© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28325
    Prev
    Next
    INDEX
    Explanations

    references to captions and footnotes in text

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

    caption

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    djangoproject
    -0.91
    ~•
    -0.76
    CONSIN
    -0.69
    РЭ
    -0.65
    fanart
    -0.63
    AlterField
    -0.63
     Her
    -0.62
     Miles
    -0.62
    posedge
    -0.60
     sfera
    -0.59
    POSITIVE LOGITS
     caption
    1.49
     captions
    1.44
     Captions
    1.31
     Caption
    1.30
    caption
    1.26
    Caption
    1.10
     captioned
    1.08
     Cassini
    0.88
    eroy
    0.82
     Roskov
    0.77
    Activations Density 0.035%

    No Known Activations