© 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. 4012
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly those involving JSON and programming function syntax

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

    Code snippets or code-related formatting

    np_acts-logits-general · gemini-2.0-flash

    technical documentation, code, and articles

    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
     Италијани
    -0.77
    orianCalendar
    -0.71
    </em>
    -0.68
     HttpNotFound
    -0.67
    createTextNode
    -0.67
    CodedInputStream
    -0.67
    IContainer
    -0.66
    thenReturn
    -0.66
     <=",
    -0.65
    DockStyle
    -0.64
    POSITIVE LOGITS
    ```
    1.04
     ```
    0.85
    CloseOperation
    0.56
    EndContext
    0.52
     kna
    0.50
     приве
    0.50
     communiquez
    0.48
     toes
    0.47
    CRIP
    0.47
     Mene
    0.47
    Activations Density 0.144%

    No Known Activations