© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7808
    Prev
    Next
    INDEX
    Explanations

    specific sequences of letters that form parts of words or proper names

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

    Citations with bracketed author and year

    np_acts-logits-general · gemini-2.0-flash

    Warlimont names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.57
     iniciales
    -0.47
    wanych
    -0.46
     xong
    -0.43
     بيها
    -0.42
    abstractmethod
    -0.42
    सन्दर्भ
    -0.42
    AbsolutePath
    -0.42
     painfully
    -0.42
    lenburg
    -0.42
    POSITIVE LOGITS
    expandindo
    0.92
     مرئيه
    0.74
    TagHelper
    0.72
     GenerationType
    0.71
    ngdoc
    0.69
    transQ
    0.69
    Dış
    0.68
    routeProvider
    0.65
     varargin
    0.65
     pector
    0.64
    Activations Density 0.575%

    No Known Activations