Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10216
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating possibility or potential outcomes

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

    "could be"

    np_acts-logits-general · gemini-2.0-flash

    potential or possibility

    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
     viewType
    -0.96
     CURIAM
    -0.86
    InvalidProtocol
    -0.85
     FontWeight
    -0.79
    soort
    -0.76
    WriteTagHelper
    -0.74
    DockStyle
    -0.72
    IANGLES
    -0.72
    ControllerAdvice
    -0.71
    dafx
    -0.71
    POSITIVE LOGITS
     potentially
    1.24
     possibly
    1.16
     conceivably
    1.13
    potentially
    0.96
     theoretically
    0.92
     easily
    0.89
     well
    0.88
     possible
    0.88
    possibly
    0.83
     Possibly
    0.83
    Activations Density 0.081%

    No Known Activations