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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1258
    Prev
    Next
    INDEX
    Explanations

    HTML elements or tags

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

    Code snippets or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    code blocks or math environments

    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
    CppMethod
    -0.63
    stdc
    -0.63
     defStyleAttr
    -0.59
    HideFlags
    -0.59
     ويكيميديا
    -0.58
     Bayard
    -0.57
     "..\..\
    -0.55
    elcome
    -0.55
    ########.
    -0.54
    esgue
    -0.54
    POSITIVE LOGITS
    cshtml
    0.73
     ModelExpression
    0.69
    ContentAsync
    0.61
    +#+
    0.56
     发表于
    0.56
    WriteAttribute
    0.54
    DMETHOD
    0.53
    ArrowToggle
    0.50
    клопе
    0.50
     kife
    0.49
    Activations Density 0.021%

    No Known Activations