© 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. 3-GEMMASCOPE-RES-16K
    6. 12252
    Prev
    Next
    INDEX
    Explanations

    instances of variable assignments and null checks in code

    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
    atoday
    -0.51
    cX
    -0.51
    <tfoot>
    -0.51
    +:+
    -0.50
    ROIT
    -0.50
    eburger
    -0.49
    Tikang
    -0.48
    }{*}{
    -0.47
    BagConstraints
    -0.47
    clang
    -0.47
    POSITIVE LOGITS
     propOrder
    0.89
     Houſe
    0.67
     cref
    0.66
     Reſ
    0.65
    assertNotNull
    0.63
     SafeMath
    0.63
     DBNull
    0.62
     []:
    0.58
    VIAF
    0.58
     diſt
    0.56
    Activations Density 0.346%

    No Known Activations