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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 319
    Prev
    Next
    INDEX
    Explanations

    instances of the word "follow" and its variations, indicating a focus on the concept of following or pursuing actions or ideas

    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
    #
    -0.60
     initComponents
    -0.50
    nically
    -0.48
     fometimes
    -0.48
    quinas
    -0.48
    wußt
    -0.48
    chmal
    -0.47
    MigrationBuilder
    -0.47
    éril
    -0.46
     canary
    -0.44
    POSITIVE LOGITS
    Follow
    1.23
     Follow
    1.20
     follow
    1.16
     FOLLOW
    1.13
    follow
    1.11
     Follows
    1.06
    FOLLOW
    1.03
     follows
    1.02
    ofollow
    0.96
    follows
    0.93
    Activations Density 0.191%

    No Known Activations