Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5885
    Prev
    Next
    INDEX
    Explanations

    email addresses or mentions of individuals using 'impact factory' and related terms

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

    starting with "Re", "Di", "An", "In", "Con", "Per" or "Sh"

    np_acts-logits-general · gemini-2.0-flash

    Impact Factory

    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
    ecutive
    -0.92
     CreateTagHelper
    -0.85
    æa
    -0.83
    ratulations
    -0.82
    ercises
    -0.81
    帖最后由
    -0.80
     I
    -0.79
    elaar
    -0.79
    icorn
    -0.78
    equations
    -0.76
    POSITIVE LOGITS
     Reſ
    1.05
     Diſ
    0.98
     Shakspeare
    0.92
     Anſ
    0.92
     Inſ
    0.88
     moschino
    0.87
     Shaksp
    0.85
     Conſ
    0.85
     Perſ
    0.84
    ſelf
    0.84
    Activations Density 0.914%

    No Known Activations