© 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. 12-GEMMASCOPE-RES-16K
    6. 16159
    Prev
    Next
    INDEX
    Explanations

    expressions related to desire or intention

    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
    kaç
    -0.54
    áló
    -0.49
    Observation
    -0.47
     Ketten
    -0.45
     chauff
    -0.45
     gimnasio
    -0.45
    クセ
    -0.44
     المحت
    -0.43
     sao
    -0.43
     campagnes
    -0.43
    POSITIVE LOGITS
    PreExecute
    0.77
    PasswordEncoder
    0.72
    prepareStatement
    0.71
    endphp
    0.70
     doInBackground
    0.67
    getSeconds
    0.67
    tagHelperRunner
    0.67
    хьтан
    0.67
    addCriterion
    0.65
     ddelweddau
    0.65
    Activations Density 0.122%

    No Known Activations