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. 1141
    Prev
    Next
    INDEX
    Explanations

    numerical values and their occurrences in a structured format

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

    Hexadecimal byte code

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal codes or SW/NA

    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
    ômico
    -0.59
    NameInMap
    -0.57
    roek
    -0.57
    EndProject
    -0.53
    存于互联网档案馆
    -0.51
    matchCondition
    -0.51
    expandindo
    -0.49
    msgTypes
    -0.48
     Numerade
    -0.48
     مشين
    -0.46
    POSITIVE LOGITS
    EA
    0.73
    da
    0.72
    ta
    0.70
    XA
    0.69
    ja
    0.69
    NA
    0.69
    la
    0.68
    ua
    0.68
    LLA
    0.68
    ka
    0.68
    Activations Density 0.251%

    No Known Activations