© 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. 21-GEMMASCOPE-RES-16K
    6. 2106
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating action or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -0.62
     [*]
    -0.60
     Afraid
    -0.58
     sockaddr
    -0.58
     useAppContext
    -0.56
    Portail
    -0.56
    EndInit
    -0.56
    IUrlHelper
    -0.53
    AddressBook
    -0.52
    inya
    -0.51
    POSITIVE LOGITS
     indeed
    0.76
     not
    0.64
    듦
    0.54
    Semitism
    0.53
    utex
    0.53
     således
    0.52
    indeed
    0.51
     Juifs
    0.51
    honneur
    0.51
    ","");
    0.51
    Activations Density 0.113%

    No Known Activations