© 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 565
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or conditions surrounding items or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    elements related to evidence in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    its, it, and its variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     these
    -0.89
     These
    -0.86
    These
    -0.74
    these
    -0.74
     including
    -0.72
     themselves
    -0.70
    それぞれの
    -0.69
    这些
    -0.69
    這些
    -0.68
    themselves
    -0.68
    POSITIVE LOGITS
     its
    0.93
    Its
    0.92
     itself
    0.85
    它是
    0.85
    它
    0.83
    因为它
    0.82
    它的
    0.82
     Its
    0.80
     financières
    0.80
     Itself
    0.78
    Activations Density 0.432%

    No Known Activations