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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4268
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure within a document

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

    HTML tags or attributes

    np_acts-logits-general · gemini-2.0-flash

    HTML start tags or code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.63
    SuppressLint
    -0.58
    oflavin
    -0.57
    enterOuterAlt
    -0.56
    OGND
    -0.55
    setupUi
    -0.55
    JsonPropertyName
    -0.54
    大家好
    -0.54
    ContentAsync
    -0.53
    stateProvider
    -0.53
    POSITIVE LOGITS
    __*/
    0.57
    tableFuture
    0.51
     समीक्षाओं
    0.49
     desear
    0.49
     wishing
    0.47
    :"-"`
    0.47
    <tfoot>
    0.46
     Pagination
    0.46
     دیکھیے
    0.46
    tanleria
    0.46
    Activations Density 0.057%

    No Known Activations