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. 3-GEMMASCOPE-RES-16K
    6. 8446
    Prev
    Next
    INDEX
    Explanations

    words related to capabilities and functionalities, particularly in technical or operational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.74
    Nicky
    -0.67
    unjung
    -0.66
    zieży
    -0.66
    labelledby
    -0.65
    SerializedName
    -0.65
    StructEnd
    -0.64
    usia
    -0.63
     Nestor
    -0.63
    ckeys
    -0.62
    POSITIVE LOGITS
     capability
    2.69
     capabilities
    2.60
     Capability
    2.45
     Capabilities
    2.34
    capability
    2.16
    Capability
    2.07
     capable
    2.06
    Capabilities
    1.91
    capabilities
    1.88
     capa
    1.88
    Activations Density 0.072%

    No Known Activations