© 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. 8109
    Prev
    Next
    INDEX
    Explanations

    specific references to licensing and author attribution in documents

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

    Code comments or parts of code

    np_acts-logits-general · gemini-2.0-flash

    Fabrice Bellard

    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
    سطس
    -0.59
    webElementGuid
    -0.55
     مشين
    -0.54
    #
    -0.54
     Coh
    -0.53
     }}"></
    -0.53
     torchvision
    -0.52
    <?
    -0.52
    kloped
    -0.51
     }}"
    -0.50
    POSITIVE LOGITS
    parsedMessage
    0.70
     nakalista
    0.55
    ůvod
    0.55
    abestanden
    0.49
    енча
    0.49
     ſtate
    0.48
     nargin
    0.45
     GenerationType
    0.45
     sumpay
    0.44
    WithMany
    0.44
    Activations Density 0.157%

    No Known Activations