© 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. 22-GEMMASCOPE-RES-16K
    11. 10569
    Prev
    Next
    INDEX
    Explanations

    references to processes related to communication and interaction

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

    Follows nouns, often related to evaluation or change

    np_acts-logits-general · gemini-2.0-flash

    collapse to

    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
     يتيمه
    -0.68
    таратура
    -0.58
    المراجع
    -0.57
    يميديا
    -0.56
     Exactos
    -0.56
    ifrance
    -0.55
    VIAF
    -0.55
     esternos
    -0.55
    Hentet
    -0.53
    Cyfeiriadau
    -0.53
    POSITIVE LOGITS
     the
    1.56
     those
    1.40
     their
    1.39
     your
    1.29
     our
    1.25
     them
    1.19
     these
    1.17
     its
    1.16
     his
    1.14
     this
    1.08
    Activations Density 0.810%

    No Known Activations