© 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. 22-GEMMASCOPE-RES-16K
    11. 13582
    Prev
    Next
    INDEX
    Explanations

    sections or elements that are empty or contain no significant content

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

    Preceding "References" or "Category"

    np_acts-logits-general · gemini-2.0-flash

    Category:

    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
    Enlaces
    -0.55
    Ссылки
    -0.51
    Климат
    -0.50
     extends
    -0.49
    Eksterne
    -0.49
     by
    -0.48
    охра
    -0.48
    di
    -0.47
    ABUL
    -0.47
     }
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.94
    دانشنامهٔ
    0.80
    脚注の使い方
    0.75
     nahilalakip
    0.70
    drawal
    0.70
    bibinfo
    0.68
    featureID
    0.66
    évaluateur
    0.66
    存于互联网档案馆
    0.65
     reciprocity
    0.63
    Activations Density 0.057%

    No Known Activations