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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6177
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and their corresponding data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.87
    AxisAlignment
    -0.86
    TagMode
    -0.84
    存于互联网档案馆
    -0.82
     nakalista
    -0.77
    IntoConstraints
    -0.77
     noqa
    -0.77
    ReusableCell
    -0.74
    RepeatedField
    -0.74
     AssemblyCulture
    -0.72
    POSITIVE LOGITS
     NgModule
    0.58
    val
    0.45
    NSMutableArray
    0.44
    ::~
    0.42
    ↵↵
    0.41
     org
    0.41
    ,
    0.41
    es
    0.41
    rxjs
    0.41
     Increasing
    0.41
    Activations Density 0.277%

    No Known Activations