© 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. 4952
    Prev
    Next
    INDEX
    Explanations

    user-directed decision-making phrases and responsibilities

    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
    TagMode
    -0.71
     CreateTagHelper
    -0.66
    Personendaten
    -0.64
    ViewImports
    -0.61
    #+#
    -0.60
    __);
    -0.58
    sidemargin
    -0.56
     TextAppearance
    -0.56
    ミナル
    -0.53
    ViewFeatures
    -0.52
    POSITIVE LOGITS
     decide
    0.83
     discretion
    0.82
     Decide
    0.78
     decides
    0.76
     decision
    0.73
     whatever
    0.70
     decisión
    0.70
     choice
    0.69
     deciding
    0.69
    Decide
    0.68
    Activations Density 0.266%

    No Known Activations