© 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. 22-GEMMASCOPE-RES-16K
    6. 9059
    Prev
    Next
    INDEX
    Explanations

    references to elevation or positioning in relation to "above" and "below."

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

    Text near "above" or "below"

    np_acts-logits-general · gemini-2.0-flash

    above and below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
     kasarigan
    -0.65
    DrawerToggle
    -0.63
    orianCalendar
    -0.60
    PropertyChanging
    -0.59
    pulumi
    -0.59
    colgroup
    -0.59
    Хьажоргаш
    -0.56
    VolleyError
    -0.56
    knex
    -0.55
     SqlConnection
    -0.53
    POSITIVE LOGITS
    mentioned
    1.15
    ground
    0.97
     ExecuteAsync
    0.81
     mentioned
    0.80
     reproach
    0.75
     ground
    0.75
     Mentioned
    0.72
    grade
    0.67
    board
    0.67
    ABOVE
    0.66
    Activations Density 0.096%

    No Known Activations