© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4369
    Prev
    Next
    INDEX
    Explanations

    specific numerical and event-related details, particularly those related to fundraising activities

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

    words and numbers related to exercise repetitions and athletic performance metrics.

    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
    Personendaten
    -0.53
    疾
    -0.44
    MouseAdapter
    -0.44
    sailing
    -0.44
     الحره
    -0.43
    racing
    -0.43
    发表于
    -0.42
     racing
    -0.40
    ству
    -0.40
    tikzpicture
    -0.40
    POSITIVE LOGITS
     lifting
    0.90
     barbell
    0.83
     lifts
    0.82
     lift
    0.81
    Lifting
    0.79
     Lifting
    0.78
    lifts
    0.72
     Lift
    0.71
    lifting
    0.71
     Weights
    0.71
    Activations Density 0.090%

    No Known Activations