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. 13-GEMMASCOPE-RES-16K
    6. 12329
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and functions

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     profilo
    -0.63
     profili
    -0.56
     Reiss
    -0.55
     Efq
    -0.55
     profiles
    -0.53
    ividual
    -0.53
    endalikan
    -0.53
    listdir
    -0.52
     profile
    -0.52
    lccn
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.79
    brainly
    0.75
    rrggbb
    0.68
    bcryptjs
    0.68
     SafeMath
    0.66
    EndContext
    0.63
    InputTagHelper
    0.62
    AddTagHelper
    0.62
     subtraction
    0.61
    ThroughAttribute
    0.60
    Activations Density 0.808%

    No Known Activations