© 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. 8670
    Prev
    Next
    INDEX
    Explanations

    structured data or attributes, particularly related to numerical representations and their configurations

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

    hexadecimal numbers and numeric values in code or mathematical notation.

    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
     Chwiliwch
    -0.72
    IsContent
    -0.68
    IsMutable
    -0.64
    ImageContext
    -0.61
     مشين
    -0.57
    FieldBuilder
    -0.57
    URLException
    -0.54
    riwal
    -0.54
    InjectAttribute
    -0.54
    httphttps
    -0.52
    POSITIVE LOGITS
    Grü
    0.36
    systemctl
    0.35
    Senator
    0.33
     tenerife
    0.32
    Jerusalem
    0.31
    Rabbi
    0.31
    Councillor
    0.31
    Overall
    0.31
     Rabbi
    0.31
    Guinea
    0.31
    Activations Density 1.561%

    No Known Activations