© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 7454
    Prev
    Next
    INDEX
    Explanations

    verbs related to arrival or instances of coming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nader
    -0.79
    IContainer
    -0.77
    nyder
    -0.71
    tető
    -0.69
    schul
    -0.68
     Liège
    -0.65
     Zahn
    -0.65
    gatron
    -0.65
     Escolar
    -0.65
    pædia
    -0.64
    POSITIVE LOGITS
    Comes
    1.55
    Came
    1.46
     Comes
    1.44
     comes
    1.43
     Came
    1.39
     COMES
    1.36
     COME
    1.35
     come
    1.33
    came
    1.30
     cometh
    1.28
    Activations Density 0.085%

    No Known Activations