© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13812
    Prev
    Next
    INDEX
    Explanations

    instances of intentionality and deliberate actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    intent or purpose

    np_acts-logits-general · gemini-2.0-flash

    acting intentionally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tiefen
    -0.35
    ReusableCell
    -0.35
    LabelTagHelper
    -0.29
     оте
    -0.28
    Niveau
    -0.27
     Zwiebel
    -0.26
     salvación
    -0.26
     Trä
    -0.25
     ultimate
    -0.25
     PLWABN
    -0.25
    POSITIVE LOGITS
     intentionally
    2.59
     deliberately
    2.52
     purposely
    2.47
     intentional
    2.36
     purposefully
    2.33
     deliberate
    2.22
     Deliber
    2.02
    故意
    1.88
     consciously
    1.88
     sengaja
    1.85
    Activations Density 0.880%

    No Known Activations