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. 5-GEMMASCOPE-RES-16K
    6. 1103
    Prev
    Next
    INDEX
    Explanations

    tags and structures related to HTML or XML code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NDEBUG
    -0.64
    stateProvider
    -0.63
    andExpect
    -0.57
    havior
    -0.56
    andReturn
    -0.56
     linkovi
    -0.54
    Acab
    -0.54
     Santander
    -0.53
    iyaki
    -0.53
    béco
    -0.52
    POSITIVE LOGITS
    SourceChecksum
    0.67
    FunctionFlags
    0.65
    tagHelperRunner
    0.65
     arşivlendi
    0.64
    ViewImports
    0.63
    TagMode
    0.59
     дописавши
    0.57
    SequentialGroup
    0.56
     Signalez
    0.54
    getOut
    0.53
    Activations Density 0.096%

    No Known Activations