© 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. 25-GEMMASCOPE-RES-16K
    11. 873
    Prev
    Next
    INDEX
    Explanations

    questioning statements or inquiries about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    them
    -0.96
     them
    -0.84
    these
    -0.81
    这两个
    -0.71
    These
    -0.70
     These
    -0.70
    those
    -0.69
    Those
    -0.68
     these
    -0.68
    you
    -0.67
    POSITIVE LOGITS
     anyone
    0.97
     anybody
    0.89
     everyone
    0.82
     everybody
    0.79
    anyone
    0.75
     Anybody
    0.74
     Anyone
    0.67
     ANYONE
    0.66
     Everyone
    0.65
    Anybody
    0.64
    Activations Density 0.167%

    No Known Activations