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

    Neuronpedia

    APICircuit 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. 11-GEMMASCOPE-RES-16K
    6. 6187
    Prev
    Next
    INDEX
    Explanations

    identifiers and numerical values in a programming or technical context

    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
    hta
    -0.50
     heur
    -0.50
     Innoc
    -0.49
     boya
    -0.48
    stance
    -0.46
    ایک
    -0.46
    </>
    -0.45
    imet
    -0.45
    <tfoot>
    -0.44
    Coefficient
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.84
     فريبيس
    0.76
    posedge
    0.69
    GenerationType
    0.65
    :✨
    0.65
    FDRE
    0.64
    IBarButtonItem
    0.64
    igshid
    0.64
     المعيارى
    0.63
    StackNavigator
    0.63
    Activations Density 0.083%

    No Known Activations