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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15354
    Prev
    Next
    INDEX
    Explanations

    references to different types of beads used in various methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wainwright
    -0.85
    Lili
    -0.79
     Lili
    -0.77
    ariConfig
    -0.75
     Wain
    -0.74
    hikari
    -0.74
    picable
    -0.74
     lí
    -0.71
    trange
    -0.71
     Romo
    -0.71
    POSITIVE LOGITS
     beads
    1.95
    Bead
    1.93
     Bead
    1.93
     Beads
    1.89
     bead
    1.82
    bead
    1.64
    beads
    1.62
     beaded
    1.15
     كومونز
    0.89
     perles
    0.84
    Activations Density 0.019%

    No Known Activations