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. 1733
    Prev
    Next
    INDEX
    Explanations

    phrases discussing benefits and arguments related to sustainability and business practices

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

    something is already done

    np_acts-logits-general · gemini-2.0-flash

    already / before / previously

    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
    DotNetBar
    -0.48
    ANDOM
    -0.44
    djangoproject
    -0.44
    DataAnnotations
    -0.41
    putInt
    -0.41
     Avent
    -0.41
    ungere
    -0.40
    Numerology
    -0.40
    ときの
    -0.39
    QtCore
    -0.39
    POSITIVE LOGITS
     already
    1.60
    already
    1.48
     Already
    1.36
    Already
    1.32
     ALREADY
    1.27
     déjà
    1.23
    ALREADY
    1.12
     redan
    1.12
     allerede
    1.11
     이미
    1.08
    Activations Density 0.603%

    No Known Activations