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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 2922
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions, particularly "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eadilan
    -0.60
    intem
    -0.58
     WIRE
    -0.52
     FetchType
    -0.52
    sifs
    -0.51
    getMinutes
    -0.50
    :+:
    -0.49
    WERS
    -0.48
     electrodes
    -0.47
    likte
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.61
    CloseOperation
    0.58
    :✨
    0.57
     Roskov
    0.57
    TagHelper
    0.56
    ConstraintMaker
    0.55
    fjspx
    0.55
    ✭✭
    0.53
    ArrowToggle
    0.52
    égard
    0.52
    Activations Density 0.126%

    No Known Activations