© 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. 4062
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence structures

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

    Text following a question/answer marker

    np_acts-logits-general · gemini-2.0-flash

    reply or answer

    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
    ✨:
    -0.65
    ListItemIcon
    -0.63
    verwijspagina
    -0.62
    جوايز
    -0.62
    '}),
    -0.62
    dillera
    -0.61
    ^(@)
    -0.59
    uroy
    -0.59
    lioz
    -0.58
    ️⃣
    -0.58
    POSITIVE LOGITS
    Reply
    0.73
    LikeLike
    0.72
     I
    0.66
     reply
    0.62
    REPLY
    0.60
     Reply
    0.60
     answer
    0.60
    </blockquote>
    0.59
     ANSWER
    0.59
    reply
    0.58
    Activations Density 0.663%

    No Known Activations