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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6703
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives often related to degree or manner of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plads
    -0.65
     houſe
    -0.64
     ſtate
    -0.63
     avoient
    -0.63
     ſche
    -0.61
     hjælp
    -0.59
     Houſe
    -0.59
     hendes
    -0.58
     hjelp
    -0.56
     suiv
    -0.55
    POSITIVE LOGITS
    tically
    0.87
    sively
    0.83
    denly
    0.79
    ally
    0.79
    ALLY
    0.78
    mically
    0.77
    quely
    0.75
    marily
    0.74
    ctively
    0.74
    ently
    0.71
    Activations Density 0.771%

    No Known Activations