© 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. 10181
    Prev
    Next
    INDEX
    Explanations

    key-value pairs and object manipulations in programming code

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

    Accessing keys or objects within dictionaries/settings

    np_acts-logits-general · gemini-2.0-flash

    dictionary keys and values

    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
     HasFactory
    -0.69
    ConstraintMaker
    -0.68
    aarrggbb
    -0.63
    JoinTable
    -0.63
    endpush
    -0.63
    ագրություններ
    -0.61
    indelijk
    -0.61
    (!__
    -0.59
    onViewCreated
    -0.59
    yii
    -0.58
    POSITIVE LOGITS
     keys
    0.84
    keys
    0.82
    Keys
    0.79
     key
    0.71
     Keys
    0.68
     Key
    0.63
    Key
    0.62
     KEYS
    0.61
     KEY
    0.59
    KEYS
    0.59
    Activations Density 0.085%

    No Known Activations