© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15049
    Prev
    Next
    INDEX
    Explanations

    technical terms and attributes related to software development and assembly configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.83
    ()]);
    -0.70
    PerformLayout
    -0.66
    
    -0.65
    FunctionFlags
    -0.64
    SourceChecksum
    -0.63
    )]);
    -0.62
    AccessorTable
    -0.61
     Audiodateien
    -0.60
     vaj
    -0.60
    POSITIVE LOGITS
    cshtml
    1.12
    UseVisualStyle
    1.10
     (!__
    1.05
     rgba
    0.76
    AxisAlignment
    0.72
    rgba
    0.69
     beginnetje
    0.68
     enfans
    0.67
     avoient
    0.67
     TextAppearance
    0.67
    Activations Density 0.005%

    No Known Activations