© 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. 35-GEMMASCOPE-RES-16K
    11. 14451
    Prev
    Next
    INDEX
    Explanations

    procedural and comparative phrases that indicate steps in a methodology or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.53
     kyllä
    -0.44
    いかがでしょうか
    -0.43
     jopa
    -0.43
     paljon
    -0.43
     certes
    -0.42
    いかが
    -0.42
    исленность
    -0.41
     pourtant
    -0.41
    muito
    -0.40
    POSITIVE LOGITS
     avoid
    1.10
    avoid
    0.91
    方便
    0.87
     convenience
    0.84
     easier
    0.84
     Avoid
    0.82
     avoiding
    0.79
     prevent
    0.79
     avoids
    0.77
    Avoid
    0.76
    Activations Density 0.808%

    No Known Activations