© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14572
    Prev
    Next
    INDEX
    Explanations

    numerical data and patterns related to measurements or results

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

    Characters used in tables and code

    np_acts-logits-general · gemini-2.0-flash

    *** markers

    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
    jfree
    -0.54
    Filmografie
    -0.50
    benhavn
    -0.48
    steamcommunity
    -0.47
     sûr
    -0.47
    windig
    -0.45
    usepackage
    -0.45
    appé
    -0.43
    bentukan
    -0.42
     ioutil
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.91
     للاسماء
    0.91
    cshtml
    0.88
    Personensuche
    0.84
    Personendaten
    0.82
    ItemBackground
    0.82
    enumii
    0.81
     Signalez
    0.79
     виправивши
    0.76
     ***!
    0.75
    Activations Density 0.273%

    No Known Activations