© 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. 16-GEMMASCOPE-RES-16K
    11. 5295
    Prev
    Next
    INDEX
    Explanations

    terms associated with habitual actions or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    like "also", "still", and "then"

    np_acts-logits-general · gemini-2.0-flash

    also / then / still / only followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.87
     Theſe
    -0.87
     Chriftian
    -0.79
     Efq
    -0.79
     becauſe
    -0.76
     pleaſure
    -0.69
     ftate
    -0.68
     Diſ
    -0.67
     purpoſe
    -0.67
     Eſ
    -0.66
    POSITIVE LOGITS
     also
    1.07
     not
    1.03
     likely
    1.01
     going
    0.95
     always
    0.95
     still
    0.92
     actually
    0.88
     able
    0.87
     just
    0.85
     considered
    0.84
    Activations Density 0.289%

    No Known Activations