Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6407
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related structures in text

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

    HTML heading tags (<h1>, <h2>, etc.)

    np_acts-logits-general · gemini-2.0-flash

    HTML headings

    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
    Koz
    -0.48
              
    -0.46
    .”
    -0.45
    Leonard
    -0.43
    Avery
    -0.43
     Leonard
    -0.43
    Lenny
    -0.42
     Lari
    -0.42
    DCT
    -0.41
    Acu
    -0.39
    POSITIVE LOGITS
    </h1>
    0.89
    <h1>
    0.89
    VersionUID
    0.71
     ProtoMessage
    0.67
     ```
    0.67
    ########.
    0.67
    `{.
    0.67
    UnknownFieldSet
    0.66
     }{@
    0.65
    KommentareTeilen
    0.65
    Activations Density 0.225%

    No Known Activations