© 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. 8879
    Prev
    Next
    INDEX
    Explanations

    formatting or syntax elements in code, particularly related to string interpolation

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

    Code-related tokens and symbols

    np_acts-logits-general · gemini-2.0-flash

    .h5 .sql .columns .

    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
    ThroughAttribute
    -0.62
    :],
    -0.58
     MainAxisSize
    -0.54
    __':
    -0.53
    itinéraire
    -0.51
    '][$
    -0.51
     فريبيس
    -0.51
    twimg
    -0.51
    """,
    -0.50
    .},
    -0.50
    POSITIVE LOGITS
     mergeFrom
    0.64
     CreateTagHelper
    0.63
    DockStyle
    0.60
    EndGlobalSection
    0.53
     Catawiki
    0.53
    kologi
    0.52
    elemField
    0.51
    fortawesome
    0.51
    apunov
    0.50
     незавершена
    0.50
    Activations Density 0.074%

    No Known Activations