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. 3-GEMMASCOPE-RES-16K
    6. 6007
    Prev
    Next
    INDEX
    Explanations

    patterns of conjunction and specificity in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tas
    -0.47
     trails
    -0.47
    lisle
    -0.45
    gy
    -0.45
    chata
    -0.44
     мно
    -0.43
    adell
    -0.43
     setInterval
    -0.42
     traceback
    -0.42
     trail
    -0.42
    POSITIVE LOGITS
    SourceChecksum
    0.78
    MLLoader
    0.77
    DebuggerStep
    0.65
    RegistryLite
    0.63
     Picchu
    0.61
    CodeAttribute
    0.60
    ConstraintMaker
    0.59
     "..\..\..\
    0.58
    новниш
    0.58
    rungsseite
    0.58
    Activations Density 0.285%

    No Known Activations