© 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. 22-GEMMASCOPE-RES-16K
    6. 7775
    Prev
    Next
    INDEX
    Explanations

    educational qualifications and academic backgrounds in biographical contexts

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

    Academic or professional achievements

    np_acts-logits-general · gemini-2.0-flash

    education and career achievements

    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
    لينكات
    -0.56
    ulite
    -0.52
    rinks
    -0.52
    IContainer
    -0.52
    AddHtmlAttribute
    -0.51
    abetes
    -0.50
    OGND
    -0.50
    matchCondition
    -0.49
     MMMM
    -0.48
    wies
    -0.47
    POSITIVE LOGITS
     studying
    1.46
     graduated
    1.38
     study
    1.37
     studied
    1.37
     Studying
    1.32
     graduating
    1.30
     enrolled
    1.27
    Studying
    1.27
     graduate
    1.23
     estudi
    1.20
    Activations Density 0.351%

    No Known Activations