© 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. 22-GEMMASCOPE-RES-16K
    6. 13634
    Prev
    Next
    INDEX
    Explanations

    instances of the word "come" in various forms and contexts

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

    phrases beginning with the word "come".

    oai_token-act-pair · gpt-4oTriggered by @christianthto

    "Come" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    come + preposition/direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UnityEditor
    -0.68
     dafs
    -0.65
    kloped
    -0.64
    BindView
    -0.63
    ismus
    -0.58
    nonatomic
    -0.56
    WebControls
    -0.56
     Xunit
    -0.55
    ism
    -0.55
     strconv
    -0.54
    POSITIVE LOGITS
     PLWABN
    0.70
     ashore
    0.70
     up
    0.70
    dienne
    0.67
     down
    0.66
     alive
    0.65
     back
    0.64
     into
    0.64
    backs
    0.62
     undone
    0.60
    Activations Density 0.056%

    No Known Activations