© 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. 3-GEMMASCOPE-RES-16K
    6. 8512
    Prev
    Next
    INDEX
    Explanations

    elements related to email headers, specifically "Reply-To" and "To" fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -1.04
     defaultstate
    -0.90
    ⓧ
    -0.85
    LookAnd
    -0.83
     &___
    -0.79
    aarrggbb
    -0.74
    bootstrapcdn
    -0.74
     Signalez
    -0.73
    PerformLayout
    -0.71
    EDEFAULT
    -0.71
    POSITIVE LOGITS
     urbain
    0.56
    ดย
    0.47
     urbana
    0.45
     invitations
    0.44
     Rest
    0.43
     invitation
    0.42
     will
    0.42
     гран
    0.41
    ᾳ
    0.41
     trùng
    0.41
    Activations Density 0.037%

    No Known Activations