© 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. 21-GEMMASCOPE-RES-16K
    6. 2264
    Prev
    Next
    INDEX
    Explanations

    code structures that handle exceptions and error checking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المشاركات
    -0.56
     stethoscope
    -0.52
    recy
    -0.51
     vời
    -0.49
    惮
    -0.47
    WebElementEntity
    -0.46
    SUCCEEDED
    -0.45
    esome
    -0.45
    dini
    -0.44
     سبک
    -0.44
    POSITIVE LOGITS
    throw
    2.02
     throw
    1.64
    raise
    1.35
     Throw
    1.25
    Throw
    1.15
     throwing
    1.13
     throws
    1.09
     threw
    1.03
     thrown
    0.99
    THROW
    0.93
    Activations Density 0.141%

    No Known Activations