© 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
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4648
    Prev
    Next
    INDEX
    Explanations

    categories and organizational elements related to information formatting in documents

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

    Followed by a colon

    np_acts-logits-general · gemini-2.0-flash

    field labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.69
    webElementXpaths
    -0.63
    enumi
    -0.63
    __(/*!
    -0.59
     تانيه
    -0.58
    ⓧ
    -0.58
    tagHelperRunner
    -0.57
    exitRule
    -0.54
     חיצוניים
    -0.54
    modelBuilder
    -0.54
    POSITIVE LOGITS
    :
    1.37
    :
    0.88
     :
    0.87
    ?:
    0.63
    :[
    0.61
    :<
    0.60
    :"
    0.59
     :
    0.57
    :**
    0.57
    .:
    0.56
    Activations Density 0.660%

    No Known Activations