© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7078
    Prev
    Next
    INDEX
    Explanations

    technical terms related to brake systems and maintenance

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

    Automobile braking systems

    np_acts-logits-general · gemini-2.0-flash

    brake pads, pedal, and clutch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    -0.49
     Jefus
    -0.44
     anſ
    -0.40
     ſtand
    -0.40
     ſche
    -0.40
     télécharge
    -0.40
     grain
    -0.36
    [])
    
    -0.35
     наси
    -0.35
     createSlice
    -0.35
    POSITIVE LOGITS
     brakes
    1.11
     brake
    1.09
    brake
    1.06
     Brakes
    1.03
    Brake
    0.98
     Brake
    0.96
     braking
    0.91
    ブレーキ
    0.80
     тормо
    0.67
     freio
    0.65
    Activations Density 0.214%

    No Known Activations