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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 614
    Prev
    Next
    INDEX
    Explanations

    references to nutritional deficiencies and health-related issues

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

    references to technological or computational concepts and operations.

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

    pronouns and determiners referring to previously mentioned entities or 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
    verwijspagina
    -0.42
    serif
    -0.40
    ⤹
    -0.40
     esche
    -0.39
    RTLR
    -0.39
    ütfen
    -0.39
    OGND
    -0.38
    labus
    -0.38
    DNEY
    -0.38
    drawiam
    -0.38
    POSITIVE LOGITS
     indeed
    0.59
     however
    0.53
     surely
    0.52
     Surely
    0.50
     mainly
    0.49
    Came
    0.48
     seem
    0.47
     Came
    0.45
     belonged
    0.44
     belong
    0.43
    Activations Density 0.771%

    No Known Activations