© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 6009
    Prev
    Next
    INDEX
    Explanations

    symbols and characters that indicate formatting or list structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijani
    -0.66
    OOTDTY
    -0.54
    minlength
    -0.51
     uova
    -0.51
     QLabel
    -0.50
     везе
    -0.50
     endwhile
    -0.49
     originaux
    -0.49
     grève
    -0.49
     étoient
    -0.49
    POSITIVE LOGITS
    AutoScale
    0.74
    IGraphics
    0.72
    migrationBuilder
    0.72
    tableLayoutPanel
    0.68
    })));
    0.68
    AutoScaleMode
    0.68
     kasarigan
    0.67
     Roskov
    0.67
     initComponents
    0.64
    //});
    0.62
    Activations Density 0.006%

    No Known Activations