© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9303
    Prev
    Next
    INDEX
    Explanations

    the presence of the term 'reasonable' in various contexts, indicating discussions around reasonableness or standards of reasonability in legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.57
    posedge
    -0.51
    Ecotoxicity
    -0.50
    icitis
    -0.50
    FormTagHelper
    -0.49
    transQ
    -0.48
    Precalculus
    -0.48
     onBackPressed
    -0.48
    engagent
    -0.47
    HandlerContext
    -0.47
    POSITIVE LOGITS
     rational
    0.63
     reasonable
    0.56
     reaſon
    0.56
     canst
    0.56
    able
    0.53
     current
    0.51
     normal
    0.50
     absorb
    0.46
     reason
    0.45
     razonable
    0.44
    Activations Density 0.426%

    No Known Activations