© 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. 13273
    Prev
    Next
    INDEX
    Explanations

    terms related to assays for detecting viral tropism in HIV research

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

    preceding "file" or related to "Trofile assay"

    np_acts-logits-general · gemini-2.0-flash

    Trofile or words starting with Tro

    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
    Not in Any Lists

    No Comments

    Negative Logits
    cokinetic
    -0.59
    matics
    -0.56
     Niedersch
    -0.55
    setVerticalGroup
    -0.55
    وردار
    -0.54
     uintptr
    -0.53
    ?>"
    -0.52
     knuckle
    -0.51
    }';
    -0.51
     blindness
    -0.50
    POSITIVE LOGITS
     Tro
    0.75
    Tro
    0.66
     tro
    0.62
     TRO
    0.58
     cherchés
    0.57
    AnchorTagHelper
    0.56
    MessageTagHelper
    0.55
    TRO
    0.54
    AxisAlignment
    0.54
    CardHeader
    0.53
    Activations Density 0.127%

    No Known Activations