Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1395
    Prev
    Next
    INDEX
    Explanations

    references to construction and assembly in the context of software and hardware

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

    followed by suffixes like -ing, -able, -out, or -offs

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonode
    -0.79
     referenties
    -0.77
    GEBURTSDATUM
    -0.76
      (
    -0.68
    ложении
    -0.67
    IZER
    -0.67
    gonic
    -0.67
    naire
    -0.66
     发表于
    -0.65
    ,:]
    -0.64
    POSITIVE LOGITS
    ings
    0.95
    able
    0.94
    ability
    0.83
    downs
    0.73
    ups
    0.68
    out
    0.67
     offs
    0.66
    outs
    0.66
    offs
    0.64
    ables
    0.62
    Activations Density 0.985%

    No Known Activations