© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5307
    Prev
    Next
    INDEX
    Explanations

    questions and speculation about relationships and conditions

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

    suggesting uncertainty or possibility

    np_acts-logits-general · gemini-2.0-flash

    might possibly occur

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.44
     never
    -0.41
    ALWAYS
    -0.40
     Stamm
    -0.39
     ontvang
    -0.38
    squareup
    -0.38
     always
    -0.38
    IBOutlet
    -0.36
    ::::::::
    -0.36
     œuvres
    -0.36
    POSITIVE LOGITS
     perhaps
    1.16
     maybe
    1.13
     might
    1.13
     presumably
    1.10
     possibly
    1.06
    perhaps
    1.06
     kanske
    1.02
     Presumably
    1.02
     probably
    1.01
    maybe
    1.00
    Activations Density 1.285%

    No Known Activations