© 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. 15310
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals or essential elements in various contexts

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

    before "may," "is," or "has."

    np_acts-logits-general · gemini-2.0-flash

    words related to things

    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
     ujednoznacz
    -0.70
     poule
    -0.59
    djangoproject
    -0.57
     prevailed
    -0.55
    μερα
    -0.53
    kloped
    -0.50
     prevails
    -0.49
    postDelayed
    -0.48
    libft
    -0.47
    Trả
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    0.68
    migrationBuilder
    0.58
    matchCondition
    0.56
     noDo
    0.53
    \"");
    0.53
    SOUNDBITE
    0.51
     +%
    0.50
    AutoScaleMode
    0.50
    に使
    0.49
     menerapkan
    0.49
    Activations Density 0.744%

    No Known Activations