© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7902
    Prev
    Next
    INDEX
    Explanations

    instances of surprising or unexpected situations and feelings

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

    a reason or justification

    np_acts-logits-general · gemini-2.0-flash

    given or considering

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     noqa
    -0.76
    IUrlHelper
    -0.74
    DeleteBehavior
    -0.56
    SizeMode
    -0.56
    parsedMessage
    -0.54
    XmlEnum
    -0.52
     parce
    -0.52
     nemlig
    -0.52
    曖昧さ回避
    -0.51
     müm
    -0.50
    POSITIVE LOGITS
     considering
    1.57
    considering
    1.37
     given
    1.34
    Considering
    1.23
     Considering
    1.23
     mengingat
    1.14
    given
    1.10
     considerando
    1.09
     учиты
    1.08
    Given
    1.03
    Activations Density 0.450%

    No Known Activations