© 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. 25-GEMMASCOPE-RES-16K
    6. 12189
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to trends or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.54
     Wul
    -0.54
    Autoritní
    -0.53
    ViewImports
    -0.52
    Datuak
    -0.51
    LoadScene
    -0.51
    grima
    -0.49
     Paglinawan
    -0.48
    Viel
    -0.47
    жник
    -0.47
    POSITIVE LOGITS
    IUrlHelper
    0.56
    Посилання
    0.51
    gister
    0.50
    WSGI
    0.49
     Reverso
    0.49
    3
    0.48
    4
    0.47
    5
    0.45
    Registry
    0.45
    _));
    0.44
    Activations Density 0.622%

    No Known Activations