© 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. 1771
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to assistance or support

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

    Preceding words of encouragement ("gives," "helps," "lets," "allow")

    np_acts-logits-general · gemini-2.0-flash

    enabling or facilitating

    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
    no
    -0.40
     fallecido
    -0.39
     abiertas
    -0.38
    JPL
    -0.38
     confirmó
    -0.37
    月
    -0.37
    有人
    -0.37
    ust
    -0.37
    juang
    -0.37
     postaci
    -0.37
    POSITIVE LOGITS
    rawDesc
    0.98
    tagHelperRunner
    0.96
    帖最后由
    0.89
    GOTREF
    0.87
    MigrationBuilder
    0.85
     cherchés
    0.84
    Diwedd
    0.83
    bootstrapcdn
    0.82
    NUMX
    0.81
    فحة
    0.81
    Activations Density 0.215%

    No Known Activations