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. 11-GEMMASCOPE-RES-16K
    6. 7466
    Prev
    Next
    INDEX
    Explanations

    technical specifications and parameters related to system components and assembly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.86
    HasForeignKey
    -0.78
    GEBURTSDATUM
    -0.76
    Abitanti
    -0.72
    الحياه
    -0.70
     betweenstory
    -0.69
    createCanvas
    -0.66
    Portály
    -0.65
    MockBean
    -0.65
    LEncoder
    -0.64
    POSITIVE LOGITS
     [].
    0.83
    uxxxx
    0.74
    "]').
    0.72
    ()].
    0.72
     {.
    0.71
     @{
    0.71
    .].
    0.70
    ][:
    0.70
    ]").
    0.66
     []).
    0.63
    Activations Density 0.072%

    No Known Activations