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. 108633
    Prev
    Next
    INDEX
    Explanations

    specific names and references related to a geographic location or institution

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

    Bal, Ball, Ballymena

    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
     -
    -0.33
     sia
    -0.29
     es
    -0.27
    ∝
    -0.27
     dus
    -0.27
     nd
    -0.26
    instructor
    -0.26
    expires
    -0.26
     Hata
    -0.26
     bend
    -0.26
    POSITIVE LOGITS
    rungsseite
    1.02
    tagHelperRunner
    0.98
    Bal
    0.94
     Baller
    0.91
     Bal
    0.91
     BALL
    0.91
     Ball
    0.89
     BAL
    0.88
    Ball
    0.87
     Bala
    0.86
    Activations Density 0.015%

    No Known Activations