Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4604
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to judicial processes

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

    Precedes a verb of argumentation or speech

    np_acts-logits-general · gemini-2.0-flash

    subject argues or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    TagMode
    -0.75
    ScopeManager
    -0.62
    
    -0.60
    ftagPool
    -0.59
    Geplaatst
    -0.59
    ViewImports
    -0.58
    ArgsConstructor
    -0.54
    SourceChecksum
    -0.53
    +:+
    -0.52
    gink
    -0.51
    POSITIVE LOGITS
     says
    1.75
     states
    1.47
    says
    1.38
     notes
    1.31
     suggests
    1.28
    Says
    1.25
     explains
    1.23
     Says
    1.19
    states
    1.14
     warns
    1.13
    Activations Density 0.620%

    No Known Activations