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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 113965
    Prev
    Next
    INDEX
    Explanations

    terms related to induced experimental changes or interventions

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

    induced outcomes

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ſche
    -0.74
     plufieurs
    -0.62
     ainfi
    -0.56
     ſta
    -0.56
    étoit
    -0.54
     enfans
    -0.52
     perſon
    -0.52
     Atlántico
    -0.50
    ſelf
    -0.50
     ſch
    -0.50
    POSITIVE LOGITS
     induced
    1.93
     Induced
    1.80
    induced
    1.80
    Induced
    1.77
     induce
    1.61
     induces
    1.39
     inducing
    1.35
     induction
    1.20
     induc
    1.16
     inducement
    1.13
    Activations Density 0.020%

    No Known Activations