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. 2-GEMMASCOPE-RES-16K
    6. 6619
    Prev
    Next
    INDEX
    Explanations

    references to various types of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropra
    -0.61
     Diallo
    -0.60
    SuppressMessage
    -0.55
     Picard
    -0.55
    odenal
    -0.55
    gameserver
    -0.54
    flink
    -0.53
    getKeyCode
    -0.51
    idän
    -0.50
    bubbles
    -0.48
    POSITIVE LOGITS
     materials
    2.99
     Materials
    2.74
    Materials
    2.70
    materials
    2.64
     MATERIALS
    2.40
    MATERIALS
    2.13
     materiales
    1.83
     materiais
    1.80
     Materialien
    1.78
     matériaux
    1.75
    Activations Density 0.174%

    No Known Activations