© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10926
    Prev
    Next
    INDEX
    Explanations

    questions that assess factual accuracy or correctness

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

    Text or code that follows the word "following"

    np_acts-logits-general · gemini-2.0-flash

    the following items

    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
    contentLoaded
    -0.73
    Хьажоргаш
    -0.69
    IVEREF
    -0.64
    GOTREF
    -0.61
     ProtoMessage
    -0.59
    原始内容存档于
    -0.58
     AssemblyCulture
    -0.49
     للاسماء
    -0.49
     TextEditing
    -0.48
    GraphicsUnit
    -0.47
    POSITIVE LOGITS
     NgModule
    0.44
     following
    0.38
     הז
    0.36
    following
    0.36
    Zar
    0.36
    acebook
    0.36
    tuo
    0.35
    MathML
    0.35
    <?>>
    0.35
    接
    0.35
    Activations Density 0.832%

    No Known Activations