© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13837
    Prev
    Next
    INDEX
    Explanations

    instances of the word "follow" and its variations, indicating a focus on guidance or following instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "follow" or "following"

    np_acts-logits-general · gemini-2.0-flash

    follow and subsequent words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.55
    nically
    -0.50
    #
    -0.49
     initComponents
    -0.49
    quinas
    -0.49
    MessageState
    -0.48
    wußt
    -0.48
    dataclass
    -0.48
    chmal
    -0.47
     gewerb
    -0.46
    POSITIVE LOGITS
    Follow
    1.29
     Follow
    1.25
     follow
    1.23
    follow
    1.20
     FOLLOW
    1.17
     Follows
    1.09
     follows
    1.07
    FOLLOW
    1.05
    ofollow
    1.00
    follows
    1.00
    Activations Density 0.130%

    No Known Activations