© 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. 25-GEMMASCOPE-RES-16K
    11. 3726
    Prev
    Next
    INDEX
    Explanations

    instances of procedural or legal language related to requests and denials in a judicial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fig
    -1.53
    Fig
    -1.48
     Gov
    -1.32
     govt
    -1.27
     Govt
    -1.25
     Figs
    -1.23
     Aug
    -1.23
     Oct
    -1.21
     Nov
    -1.20
     Univ
    -1.20
    POSITIVE LOGITS
     December
    0.86
     February
    0.82
     January
    0.82
     November
    0.80
     September
    0.80
     October
    0.78
     August
    0.74
    December
    0.74
    November
    0.69
    January
    0.69
    Activations Density 0.568%

    No Known Activations