© 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. 6660
    Prev
    Next
    INDEX
    Explanations

    system error codes and their descriptions

    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
     &___
    -0.55
    DebuggerStep
    -0.54
     nakalista
    -0.54
    CompleteListener
    -0.50
    CascadeType
    -0.49
    ostante
    -0.46
    anskje
    -0.46
    FailureListener
    -0.46
     Audiodateien
    -0.45
    atser
    -0.44
    POSITIVE LOGITS
     bad
    0.71
     Bad
    0.70
     Too
    0.69
    Argument
    0.68
    Bad
    0.66
    bad
    0.65
     too
    0.64
     Argument
    0.63
     Infórmanos
    0.63
     insufficient
    0.62
    Activations Density 0.412%

    No Known Activations