© 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. 24-GEMMASCOPE-RES-16K
    6. 4221
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and programming syntax

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

    Code snippets with parentheses and arithmetic/variables

    np_acts-logits-general · gemini-2.0-flash

    exam, intent, app

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.63
    phorbia
    -0.57
     Ey
    -0.53
     Ông
    -0.50
     Attic
    -0.50
     Envelope
    -0.49
     Incl
    -0.49
    latego
    -0.49
     Eff
    -0.49
    Acct
    -0.49
    POSITIVE LOGITS
     an
    1.12
    an
    0.59
    expandindo
    0.58
    енча
    0.56
     aan
    0.56
    esModule
    0.53
     كومونز
    0.51
    帖最后由
    0.44
     anh
    0.43
     nouvel
    0.43
    Activations Density 0.459%

    No Known Activations