© 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. 8-GEMMASCOPE-RES-16K
    6. 10194
    Prev
    Next
    INDEX
    Explanations

    references to failure to appear in legal contexts and issues related to defaulting obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.58
    CppMethod
    -0.58
    pexpr
    -0.54
    MigrationBuilder
    -0.52
    Rè
    -0.52
    RenderAtEndOf
    -0.51
    protoimpl
    -0.49
     CreateTagHelper
    -0.48
    冤
    -0.48
    Története
    -0.48
    POSITIVE LOGITS
    mybatisplus
    0.69
     punctual
    0.67
     attendance
    0.66
     missed
    0.62
    ########.
    0.60
     Attendance
    0.60
    Missed
    0.59
     punct
    0.55
     puntual
    0.55
     tard
    0.55
    Activations Density 0.453%

    No Known Activations