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
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12691
    Prev
    Next
    INDEX
    Explanations

    LaTeX math syntax and formatting components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.53
     appelez
    -0.41
    principalColumn
    -0.38
    adaptiveStyles
    -0.37
    synthesize
    -0.36
     TestBed
    -0.35
    HMIS
    -0.35
    Rüyada
    -0.34
     évit
    -0.34
    canActivate
    -0.34
    POSITIVE LOGITS
     Waray
    0.57
    enumi
    0.56
     الرياضيه
    0.52
     esternos
    0.52
    addGroup
    0.49
    RTLI
    0.49
     AssemblyTitle
    0.49
    URIComponent
    0.49
    stdafx
    0.47
    extField
    0.47
    Activations Density 0.143%

    No Known Activations