© 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. 12-GEMMASCOPE-RES-16K
    11. 16078
    Prev
    Next
    INDEX
    Explanations

    keywords associated with actions or conditions related to intentionality and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reſ
    -0.65
     étoient
    -0.64
     iſt
    -0.60
     avoient
    -0.60
     fallu
    -0.58
     religieuses
    -0.58
     AssemblyCompany
    -0.58
     Anſ
    -0.56
     Tand
    -0.56
    ArgsConstructor
    -0.56
    POSITIVE LOGITS
     deliberately
    0.66
     intentionally
    0.63
    الإنجليزية
    0.60
     purposely
    0.55
     nhằm
    0.53
    あえて
    0.53
     purposefully
    0.52
     EconPapers
    0.52
     deliberate
    0.51
     intentional
    0.51
    Activations Density 0.766%

    No Known Activations