© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21003
    Prev
    Next
    INDEX
    Explanations

    sections or headings related to results and discussions in a research context

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

    section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -1.13
     يتيمه
    -1.03
    StoryboardSegue
    -1.01
    aarrggbb
    -0.98
     utafitiHapana
    -0.96
     وتسجيلات
    -0.93
     Chwiliwch
    -0.91
    RenderAtEndOf
    -0.91
    OGND
    -0.90
    хьтан
    -0.90
    POSITIVE LOGITS
    Model
    0.36
    First
    0.35
     First
    0.33
    Firstly
    0.33
     Firstly
    0.31
     Model
    0.31
    首先
    0.30
    1
    0.29
    <sup>
    0.29
    Before
    0.28
    Activations Density 0.043%

    No Known Activations