© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    information related to services, locations, and products within various contexts

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

    Commas followed by "this," "these," or articles

    np_acts-logits-general · gemini-2.0-flash

    this or these specific 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
     opérateur
    -0.60
     AspNetCore
    -0.55
     SPDX
    -0.54
    CheckedChanged
    -0.54
    
    -0.53
    ValueStyle
    -0.52
     Affiliations
    -0.50
    EDEFAULT
    -0.49
    requestCode
    -0.49
    +#+
    -0.48
    POSITIVE LOGITS
     this
    0.73
     these
    0.67
     بيها
    0.64
    this
    0.59
    these
    0.58
    !*\
    0.54
     этот
    0.53
    featureID
    0.53
     dieser
    0.53
    <bos>
    0.52
    Activations Density 0.115%

    No Known Activations