© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6650
    Prev
    Next
    INDEX
    Explanations

    elements and sequences in programming code

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

    Code snippets with keywords like "class", "public", and file extensions

    np_acts-logits-general · gemini-2.0-flash

    code blocks and programming

    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
    IsMutable
    -0.59
    WriteTagHelper
    -0.57
     makl
    -0.55
     bug
    -0.54
    الحياه
    -0.54
    beforeSend
    -0.53
    Hozzáférés
    -0.51
    MethodManager
    -0.50
     незавершена
    -0.49
     urmă
    -0.49
    POSITIVE LOGITS
    AllowAnonymous
    0.62
    rfloor
    0.56
    RenderAtEndOf
    0.55
     ComVisible
    0.55
     gainera
    0.53
     Autonomy
    0.53
    psack
    0.52
    })*/
    0.51
    utives
    0.51
     ffilmiau
    0.51
    Activations Density 0.100%

    No Known Activations