© 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. 7755
    Prev
    Next
    INDEX
    Explanations

    specific categories and attributes related to data and questions

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

    nouns and noun phrases, particularly those that are concrete objects or specific concepts.

    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
    يكب
    -0.38
    AddressBook
    -0.38
    ajur
    -0.37
    leih
    -0.37
    FormTagHelper
    -0.36
    horesis
    -0.36
    RotationOrder
    -0.35
     cejas
    -0.35
     poliéster
    -0.35
    itieren
    -0.34
    POSITIVE LOGITS
     we
    1.66
     they
    1.36
     she
    1.30
     you
    1.09
     he
    1.07
    they
    0.77
     мы
    0.77
     that
    0.76
     они
    0.73
     youre
    0.69
    Activations Density 1.679%

    No Known Activations