© 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. 16340
    Prev
    Next
    INDEX
    Explanations

    date formatting patterns and related functions in programming contexts

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

    Hours in time formats

    np_acts-logits-general · gemini-2.0-flash

    time formats hh:mm:ss

    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
    expandindo
    -0.82
    ContentAsync
    -0.76
    Datuak
    -0.74
     protoimpl
    -0.74
    errHandler
    -0.73
    tagext
    -0.68
    OGND
    -0.66
    enterOuterAlt
    -0.65
    istoitu
    -0.61
    tagHelperRunner
    -0.60
    POSITIVE LOGITS
    łaszcza
    0.52
     kereszt
    0.52
     HH
    0.51
    󠁴
    0.51
    yntaxException
    0.50
    enschappen
    0.50
    indah
    0.49
     consciência
    0.49
     SSS
    0.48
     kk
    0.48
    Activations Density 0.137%

    No Known Activations