© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 10157
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming functions and options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kung
    -0.39
     skb
    -0.38
     _("
    -0.35
     noqa
    -0.33
    Tembelea
    -0.33
    randrange
    -0.33
    PhysRevD
    -0.33
    Gambas
    -0.33
     margen
    -0.33
    EndContext
    -0.33
    POSITIVE LOGITS
    matlab
    0.73
     MATLAB
    0.69
    MATLAB
    0.65
    argout
    0.64
     Matlab
    0.63
     matlab
    0.61
    hObject
    0.61
    varargin
    0.59
     eventdata
    0.58
    chartInstance
    0.57
    Activations Density 0.213%

    No Known Activations