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. 22-GEMMASCOPE-RES-16K
    6. 12922
    Prev
    Next
    INDEX
    Explanations

    assertions related to testing properties of objects and arrays in JavaScript

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

    ). followed by toBe

    np_acts-logits-general · gemini-2.0-flash

    testing expect .toBe

    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
    DockStyle
    -0.83
    AndEndTag
    -0.72
    CodedInputStream
    -0.69
    NamedQueries
    -0.67
    Rhestr
    -0.64
    BeginContext
    -0.61
    ühen
    -0.61
     uska
    -0.60
    GetAxis
    -0.58
    ScopeManager
    -0.57
    POSITIVE LOGITS
     paille
    0.49
     سكانية
    0.48
     equal
    0.47
     antichi
    0.46
     Pública
    0.46
     vapa
    0.45
    Enllaços
    0.45
     tacón
    0.45
     vandens
    0.44
     umani
    0.43
    Activations Density 0.108%

    No Known Activations