Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3185
    Prev
    Next
    INDEX
    Explanations

    terms related to drag racing and automotive performance

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

    drag racing and pump-probe technique

    np_acts-logits-general · gemini-2.0-flash

    drag racing and femtosecond excitation

    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
    appartamento
    -0.47
    RenderAtEndOf
    -0.44
    RTEX
    -0.42
    хьтан
    -0.41
    czegóły
    -0.40
    tanleria
    -0.40
    insegna
    -0.40
     Мексичка
    -0.39
    EdgeInsets
    -0.36
    FontOfSize
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    0.59
    Drift
    0.49
     Drift
    0.48
     drifting
    0.47
     drift
    0.47
    drift
    0.44
     sleeper
    0.44
    __':
    0.44
    raire
    0.43
     onAnimation
    0.41
    Activations Density 0.182%

    No Known Activations