© 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. 28152
    Prev
    Next
    INDEX
    Explanations

    items related to layout and alignment in programming or technical documentation

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

    code declarations and structure

    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
     Sky
    -0.59
    Sky
    -0.59
     deber
    -0.54
     SKY
    -0.53
     sky
    -0.52
     AssemblyCulture
    -0.49
     CLAIMS
    -0.49
     Total
    -0.48
    zám
    -0.45
    Soul
    -0.44
    POSITIVE LOGITS
    RELATED
    1.26
    UNRELATED
    1.13
     CommonModule
    0.81
     оригіналу
    0.76
     RELATED
    0.70
     BorderSide
    0.66
     OkHttpClient
    0.66
     GenerationType
    0.64
     XNUMX
    0.63
     विश्वसनीयता
    0.63
    Activations Density 0.001%

    No Known Activations