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. 24-GEMMASCOPE-RES-16K
    6. 13984
    Prev
    Next
    INDEX
    Explanations

    historical references to governmental or organizational changes and the resulting impacts on society

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

    Following "was," "were," or "been."

    np_acts-logits-general · gemini-2.0-flash

    state of a place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.78
     المعيارى
    -0.74
     estekak
    -0.72
    AfterViewInit
    -0.69
    @[+][
    -0.68
     jPanel
    -0.67
    脚注の使い方
    -0.66
    SequentialGroup
    -0.62
    MessageTagHelper
    -0.62
    évaluateur
    -0.60
    POSITIVE LOGITS
     occupied
    1.01
     inhabited
    0.84
     visited
    0.84
     frequented
    0.81
     overrun
    0.77
     unoccupied
    0.76
     empty
    0.71
     populated
    0.71
     invaded
    0.70
     inaccessible
    0.66
    Activations Density 0.295%

    No Known Activations