© 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. 10702
    Prev
    Next
    INDEX
    Explanations

    questions regarding programming and coding tasks

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

    Followed by a sentence initial "I"

    np_acts-logits-general · gemini-2.0-flash

    examples

    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
     оригіналу
    -0.69
     صوتيه
    -0.58
    _));
    -0.56
    HasAnnotation
    -0.55
    oa̍t
    -0.54
    PreAuthorize
    -0.53
     Meksiku
    -0.52
     通販
    -0.51
    Климат
    -0.51
    ModelSerializer
    -0.51
    POSITIVE LOGITS
     example
    2.51
    Например
    2.36
     например
    2.35
     Например
    2.33
     misalnya
    2.27
     bijvoorbeeld
    2.21
    Example
    2.14
    例如
    2.13
    example
    2.12
    例えば
    2.08
    Activations Density 0.717%

    No Known Activations