© 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. 12366
    Prev
    Next
    INDEX
    Explanations

    terms and references related to medical treatments and outcomes

    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
     anch
    -0.53
    发表于
    -0.47
     kasarigan
    -0.47
    бі
    -0.47
    ientôt
    -0.46
    sivi
    -0.46
    Rüyada
    -0.45
    länd
    -0.45
    ulents
    -0.44
    ichord
    -0.44
    POSITIVE LOGITS
    URLException
    0.84
    StoryboardSegue
    0.79
     ويكيپيديا
    0.78
    endpush
    0.76
     protoimpl
    0.69
    KommentareTeilen
    0.69
    NullException
    0.68
    ArgsConstructor
    0.68
    FailureListener
    0.67
    tanleria
    0.66
    Activations Density 0.731%

    No Known Activations