© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 2415
    Prev
    Next
    INDEX
    Explanations

    terms related to legal immunity and claims against the government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    हो
    -0.47
     precisione
    -0.45
    Rujuakan
    -0.44
    StringValue
    -0.43
     diligen
    -0.43
    memberof
    -0.41
    VolleyError
    -0.41
     optique
    -0.40
    ụng
    -0.40
    ühungen
    -0.39
    POSITIVE LOGITS
     immunity
    2.05
     Immunity
    1.73
     immune
    1.67
     protected
    1.63
     protection
    1.60
    immunity
    1.58
    immune
    1.50
     Immune
    1.43
     exempt
    1.41
    Protected
    1.40
    Activations Density 0.676%

    No Known Activations