© 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. 20-GEMMASCOPE-RES-16K
    11. 7868
    Prev
    Next
    INDEX
    Explanations

    keywords related to software functionality and user actions

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

    Followed by common words

    np_acts-logits-general · gemini-2.0-flash

    peer to peer swarm, cleaning up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UFACT
    -0.58
    kug
    -0.55
     UITableViewCell
    -0.55
    noopener
    -0.55
    iosync
    -0.53
    ^(@)
    -0.53
     onPause
    -0.53
     Horv
    -0.53
    ollection
    -0.51
    dollis
    -0.51
    POSITIVE LOGITS
     […]
    1.82
    ↵
    1.79
    ,...
    1.40
     =
    1.40
     [...]
    1.40
    \\
    1.30
    ↵↵
    1.30
     ..."
    1.29
     \\
    1.27
    </h3>
    1.26
    Activations Density 7.669%

    No Known Activations