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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8966
    Prev
    Next
    INDEX
    Explanations

    concepts related to brake pad material and maintenance

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

    terminology related to vehicle brake systems and components.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.59
     createSlice
    -0.47
    stdc
    -0.43
     Jefus
    -0.43
     grain
    -0.42
     Compiled
    -0.42
     ſtand
    -0.40
    jsonwebtoken
    -0.40
    Vidite
    -0.39
     anſ
    -0.39
    POSITIVE LOGITS
     brakes
    1.07
     brake
    1.05
    brake
    1.04
     Brakes
    0.97
     braking
    0.92
    Brake
    0.92
     Brake
    0.87
    ブレーキ
    0.77
     тормо
    0.69
    bra
    0.63
    Activations Density 0.254%

    No Known Activations