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. 21-GEMMASCOPE-RES-16K
    6. 15131
    Prev
    Next
    INDEX
    Explanations

    terms related to legal judgments and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.66
    TagMode
    -0.61
    TestBed
    -0.59
     wireType
    -0.57
    RepeatedField
    -0.57
    ynı
    -0.56
    RenderAtEndOf
    -0.56
     esternos
    -0.56
     untitled
    -0.55
     ujednoznacz
    -0.54
    POSITIVE LOGITS
     appropriate
    1.54
    appropriate
    1.32
    Appropriate
    1.31
     Appropriate
    1.30
     justified
    1.25
     justifiable
    1.23
     preferable
    1.16
     warranted
    1.15
     reasonable
    1.12
     logical
    1.09
    Activations Density 0.846%

    No Known Activations