© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6925
    Prev
    Next
    INDEX
    Explanations

    code-related elements and structure in programming languages

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

    Code snippets or program names

    np_acts-logits-general · gemini-2.0-flash

    C/H/SQL/math/legal/foreign language snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.62
    mybatisplus
    -0.56
     kasarigan
    -0.53
     initComponents
    -0.53
    eapples
    -0.52
    tamol
    -0.51
     AttributeSet
    -0.50
    ölker
    -0.49
    IsMutable
    -0.49
     pyplot
    -0.48
    POSITIVE LOGITS
    SuppressLint
    0.49
     sidor
    0.47
    arangay
    0.38
     electrica
    0.36
    ⓘ
    0.36
     Lawton
    0.36
    rajz
    0.35
    Portale
    0.35
     död
    0.34
    fromnode
    0.33
    Activations Density 0.408%

    No Known Activations