© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8885
    Prev
    Next
    INDEX
    Explanations

    sections focused on study methodologies and results related to research compliance and ethical considerations

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

    section headers and structural markers in academic documents.

    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
     moreover
    -0.62
     furthermore
    -0.57
     inoltre
    -0.54
     außerdem
    -0.49
     also
    -0.48
     zudem
    -0.48
     thus
    -0.46
     however
    -0.46
     secondly
    -0.46
     übrigens
    -0.46
    POSITIVE LOGITS
    MessageOf
    0.61
    ここでは
    0.59
    General
    0.58
    __":
    
    0.53
     General
    0.53
    Below
    0.52
    Algemeen
    0.51
     Following
    0.50
     généraux
    0.50
     Général
    0.49
    Activations Density 0.631%

    No Known Activations