© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 406
    Prev
    Next
    INDEX
    Explanations

    conditional statements about requirements and eligibility

    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
    ériques
    -0.51
    vertical
    -0.48
     vertical
    -0.47
    atiche
    -0.45
    flute
    -0.43
    킹
    -0.42
     joint
    -0.42
    meral
    -0.41
    ಿದ
    -0.41
    manes
    -0.41
    POSITIVE LOGITS
    verwijspagina
    0.79
    
    0.78
    UnknownFieldSet
    0.72
     ComVisible
    0.70
    queryInterface
    0.69
    TypedDataSet
    0.67
     jScrollPane
    0.67
    enumi
    0.64
     समीक्षाओं
    0.64
     >=",
    0.63
    Activations Density 0.374%

    No Known Activations