© 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. 7823
    Prev
    Next
    INDEX
    Explanations

    second-person pronouns and phrases directed at the reader

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

    Statements starting with "you"

    np_acts-logits-general · gemini-2.0-flash

    direct address or conversation

    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
     للمعارف
    -0.58
     мәкал
    -0.58
     protoimpl
    -0.53
    ValueStyle
    -0.53
    NewUrlParser
    -0.52
    \]
    -0.51
    .*")]
    -0.48
    routeProvider
    -0.48
    NgModule
    -0.46
     administrativos
    -0.46
    POSITIVE LOGITS
     kidding
    0.81
     missed
    0.76
     shouldn
    0.73
     should
    0.69
     forgot
    0.69
     sure
    0.68
     seemed
    0.67
     said
    0.67
     mean
    0.66
     seem
    0.65
    Activations Density 0.134%

    No Known Activations