© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10734
    Prev
    Next
    INDEX
    Explanations

    legal claims and the terminology associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oswego
    -0.81
    دور
    -0.72
    ckeye
    -0.70
     Boch
    -0.70
    gesellschaft
    -0.70
    HEAST
    -0.68
    ordnungen
    -0.68
    التالي
    -0.68
     câte
    -0.67
    inoco
    -0.66
    POSITIVE LOGITS
     claims
    2.91
     claim
    2.82
     Claims
    2.76
     Claim
    2.69
    claims
    2.51
     CLAIMS
    2.50
     CLAIM
    2.47
    Claims
    2.47
    Claim
    2.47
    claim
    2.38
    Activations Density 0.126%

    No Known Activations