© 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. 12594
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing to newsletters and receiving information via email

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

    Sign up, registration, or subscribing

    np_acts-logits-general · gemini-2.0-flash

    signs up and registers

    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
    endphp
    -0.63
    PYX
    -0.55
     Felton
    -0.55
    ソッド
    -0.49
     vych
    -0.46
     revision
    -0.46
     PATENT
    -0.45
    sertation
    -0.45
     Produits
    -0.45
     Revision
    -0.45
    POSITIVE LOGITS
     sign
    2.29
     signup
    2.09
     registration
    2.08
     signing
    2.06
     Sign
    2.02
     signed
    1.96
     register
    1.94
     registering
    1.93
     SIGN
    1.93
    Sign
    1.91
    Activations Density 0.291%

    No Known Activations