© 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. 18-GEMMASCOPE-RES-16K
    11. 1640
    Prev
    Next
    INDEX
    Explanations

    conversational interactions and inquiries about offers or assistance

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

    Follows a direct quote or speech act

    np_acts-logits-general · gemini-2.0-flash

    reporting speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utdown
    -0.53
     Diri
    -0.51
    classnames
    -0.47
    publik
    -0.46
    MPN
    -0.46
    HomeAsUp
    -0.46
     publik
    -0.45
    WebServlet
    -0.45
    ngthen
    -0.45
    miştir
    -0.44
    POSITIVE LOGITS
     saying
    1.23
     said
    1.20
    说是
    1.13
     told
    1.08
     mengatakan
    1.08
     says
    1.06
    Said
    1.06
    said
    1.04
     Says
    1.04
     Said
    1.04
    Activations Density 0.353%

    No Known Activations