© 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. 5549
    Prev
    Next
    INDEX
    Explanations

    phrases discussing differences and comparisons

    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
    migrationBuilder
    -0.61
    liesslich
    -0.52
    ließlich
    -0.51
     curse
    -0.45
    curse
    -0.44
     Curse
    -0.44
    ueux
    -0.44
     autorytatywna
    -0.44
    Curse
    -0.43
    threat
    -0.43
    POSITIVE LOGITS
     difference
    3.59
     differences
    3.14
    difference
    3.11
     Difference
    2.96
    Difference
    2.86
     Differences
    2.80
     DIFFERENCE
    2.70
    Differences
    2.68
    differences
    2.66
     différence
    2.64
    Activations Density 1.123%

    No Known Activations