© 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. 22-GEMMASCOPE-RES-16K
    6. 10672
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to historical events or contexts

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

    containing diacritics, particularly "Ž" and "Ż"

    np_acts-logits-general · gemini-2.0-flash

    siteduzero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.72
     sheets
    -0.59
     sheet
    -0.58
    EndProject
    -0.57
    windowFixed
    -0.57
    AnimationsModule
    -0.56
    TPL
    -0.53
     Sheet
    -0.51
     ***!
    -0.50
     Sheets
    -0.50
    POSITIVE LOGITS
     kasarigan
    0.68
    principalColumn
    0.65
    ToMany
    0.57
     consultato
    0.56
     Dicapai
    0.52
    sidemargin
    0.49
    modelBuilder
    0.48
    rrggbb
    0.48
    IntoConstraints
    0.48
     Goodreads
    0.47
    Activations Density 0.087%

    No Known Activations