© 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. 3-GEMMASCOPE-RES-16K
    11. 5793
    Prev
    Next
    INDEX
    Explanations

    repeated sequences or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.50
    ↵↵
    -0.46
    [toxicity=0]
    -0.37
     before
    -0.34
     and
    -0.34
    Và
    -0.33
     
    -0.32
     $\
    -0.31
    ギ
    -0.31
     rồi
    -0.31
    POSITIVE LOGITS
    Personendaten
    0.92
     nakalista
    0.89
    awtextra
    0.88
     '\\;'
    0.88
    richTextPanel
    0.87
    UnusedPrivate
    0.85
    AddTagHelper
    0.85
    tagHelperRunner
    0.84
    parsedMessage
    0.84
    LookAnd
    0.82
    Activations Density 0.536%

    No Known Activations