© 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. 31-GEMMASCOPE-RES-16K
    11. 2771
    Prev
    Next
    INDEX
    Explanations

    phrases or actions associated with deletion and removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to removing, eliminating, or discontinuing something.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localVar
    -0.43
    Durée
    -0.40
     zur
    -0.39
     nowhere
    -0.37
    msgTypes
    -0.37
    价比
    -0.35
    ropriate
    -0.35
    isContained
    -0.35
    +#+#
    -0.34
     Sơ
    -0.34
    POSITIVE LOGITS
     altogether
    0.90
     kaikki
    0.71
    一切
    0.70
     wszel
    0.69
     entirely
    0.68
     hẳn
    0.65
     completely
    0.65
     całkow
    0.65
     lahat
    0.63
    Completely
    0.63
    Activations Density 0.637%

    No Known Activations