© 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. 22-GEMMASCOPE-RES-16K
    11. 10112
    Prev
    Next
    INDEX
    Explanations

    references to disproportionate effects or outcomes in various contexts

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

    followed by "ate" or "ATE"

    np_acts-logits-general · gemini-2.0-flash

    suffix -ate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -1.06
     виправивши
    -0.66
    VersionUID
    -0.58
    AllowUser
    -0.56
    typeparam
    -0.56
    FormTagHelper
    -0.54
    पया
    -0.53
     كومونز
    -0.52
    sillon
    -0.52
    urium
    -0.49
    POSITIVE LOGITS
    ate
    1.53
    ATE
    1.32
    ates
    1.18
    rate
    1.13
    ATES
    1.07
     ate
    1.01
    ately
    0.99
     rate
    0.98
    nate
    0.96
    atea
    0.94
    Activations Density 0.381%

    No Known Activations