© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6949
    Prev
    Next
    INDEX
    Explanations

    the various forms of the verb "come" used in different contexts

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

    "Come" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    come to or back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    carta
    -0.47
    ginfo
    -0.47
    utico
    -0.46
    nbsp
    -0.45
    organe
    -0.42
    ್ಯ
    -0.42
    早速
    -0.41
    nyder
    -0.41
    letoe
    -0.41
     oczywiście
    -0.40
    POSITIVE LOGITS
     GenerationType
    0.97
     Theſe
    0.95
     Efq
    0.95
    Came
    0.93
     COME
    0.92
     ſtand
    0.90
    Come
    0.90
    Comes
    0.87
     myſelf
    0.84
     Monfieur
    0.84
    Activations Density 0.062%

    No Known Activations