© 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. 23-GEMMASCOPE-RES-16K
    11. 14590
    Prev
    Next
    INDEX
    Explanations

    references to press and media events such as press conferences and press releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.68
     CreateTagHelper
    -0.52
    cedido
    -0.48
    aigu
    -0.47
    AsyncResult
    -0.46
    IsMutable
    -0.46
    BeginInit
    -0.46
    hamento
    -0.44
    geord
    -0.44
    enumi
    -0.44
    POSITIVE LOGITS
     conference
    1.03
     conferences
    1.02
     release
    0.88
     releases
    0.87
     Conference
    0.80
     Conferences
    0.80
     Releases
    0.77
    conference
    0.76
     CONFERENCE
    0.76
    Conference
    0.75
    Activations Density 0.088%

    No Known Activations