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. 10-GEMMASCOPE-RES-16K
    6. 2722
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to academic and professional achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.92
    MemoryWarning
    -0.81
    AnchorStyles
    -0.80
    awtextra
    -0.76
    SourceChecksum
    -0.74
     BoxDecoration
    -0.73
     متعلقه
    -0.70
    <>());
    -0.68
     resourceCulture
    -0.67
    новништво
    -0.66
    POSITIVE LOGITS
    AsUp
    0.71
    hiker
    0.51
     later
    0.44
    archiviato
    0.43
    apunov
    0.42
    bbene
    0.42
     Later
    0.41
     senere
    0.41
     توانند
    0.41
     bune
    0.41
    Activations Density 0.576%

    No Known Activations