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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4370
    Prev
    Next
    INDEX
    Explanations

    phrases or commands related to following or tracking something or someone

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

    "follow" and its variations

    np_acts-logits-general · gemini-2.0-flash

    follow, followed, following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppModule
    -0.63
     Greenfield
    -0.60
    styleable
    -0.59
     McCarty
    -0.59
    _^
    -0.59
     Hawley
    -0.57
    astă
    -0.56
    shells
    -0.55
     BoxFit
    -0.55
     Yag
    -0.53
    POSITIVE LOGITS
     Follows
    0.93
     suit
    0.85
     follows
    0.80
     FOLLOW
    0.77
    Followed
    0.76
     followers
    0.71
    follows
    0.71
    Follow
    0.71
    follow
    0.71
     Followed
    0.70
    Activations Density 0.172%

    No Known Activations