© 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. 15-GEMMASCOPE-RES-16K
    11. 12520
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the conditions under which compensation or accountability may apply

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↘
    -0.45
    ście
    -0.43
    imana
    -0.42
    Sources
    -0.42
     Lieber
    -0.42
    licite
    -0.41
     loc
    -0.41
    tib
    -0.41
     seria
    -0.40
    ژن
    -0.40
    POSITIVE LOGITS
     Roskov
    0.81
    seamnă
    0.78
     BorderRadius
    0.77
    setVerticalGroup
    0.73
     Reverso
    0.73
     AttributeSet
    0.72
     Wiktionnaire
    0.71
     doesn
    0.68
     kasarigan
    0.67
    未必
    0.65
    Activations Density 0.453%

    No Known Activations