© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13167
    Prev
    Next
    INDEX
    Explanations

    mentions of ketamine and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names and references, particularly in academic or scientific writing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    names starting with "Ke" such as Keisha, Keese, Kessler, or medications like ketamine.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    proper nouns and names, particularly surnames beginning with "Ke".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.61
    bootstrapcdn
    -0.59
    fjspx
    -0.58
     يتيمه
    -0.55
    CodedInputStream
    -0.55
    tvguidetime
    -0.54
     VIAF
    -0.53
     ویکی‌پدی
    -0.51
    GOTREF
    -0.49
     Exacts
    -0.46
    POSITIVE LOGITS
     Ke
    0.65
    Ke
    0.60
     Keaton
    0.50
     ke
    0.48
     Ке
    0.47
    ke
    0.46
     Kej
    0.44
     Keim
    0.42
     Kel
    0.42
     Kevin
    0.42
    Activations Density 0.220%

    No Known Activations