Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14825
    Prev
    Next
    INDEX
    Explanations

    mentions of programming languages, libraries, and specific coding constructs

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

    `std` followed by a container name

    np_acts-logits-general · gemini-2.0-flash

    C++ std library references

    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
    scher
    -0.68
    Geplaatst
    -0.66
     jadx
    -0.66
    er
    -0.64
    رير
    -0.63
     Parrish
    -0.60
     taha
    -0.59
    PerformLayout
    -0.58
     ffilm
    -0.57
     Stores
    -0.57
    POSITIVE LOGITS
     Corde
    0.81
     Bole
    0.79
     strtok
    0.73
     Domingo
    0.73
    NOST
    0.73
    DropTable
    0.73
    fycat
    0.72
    ccoli
    0.71
    Capp
    0.71
     Capp
    0.69
    Activations Density 0.831%

    No Known Activations