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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1512
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities, particularly repeating or memorable ones

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

    Tokens starting with "Sh" or "sh"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Sh

    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
    /*
    -1.02
    /**
    -0.88
    WebVitals
    -0.84
     Perak
    -0.78
     utafitiHapana
    -0.78
    ContentAsync
    -0.78
    醐
    -0.77
    ACCESS
    -0.77
    reportWebVitals
    -0.77
    tableFuture
    -0.75
    POSITIVE LOGITS
    Sh
    0.88
     Sh
    0.84
     Shanks
    0.84
     Shu
    0.82
    SH
    0.82
     Shum
    0.81
     SH
    0.81
    Shu
    0.81
    Sherry
    0.72
    sh
    0.72
    Activations Density 0.268%

    No Known Activations