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. 9-GEMMASCOPE-RES-16K
    6. 15447
    Prev
    Next
    INDEX
    Explanations

    statements related to elevation and geographic measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     turn
    -0.57
     ProtoMessage
    -0.49
    Carriera
    -0.49
    msgSender
    -0.49
     саны
    -0.47
    turn
    -0.47
    RenderAtEndOf
    -0.45
     Turn
    -0.45
    ortun
    -0.45
    WithIOException
    -0.45
    POSITIVE LOGITS
     altitude
    0.93
     Altitude
    0.81
     altitudes
    0.81
     elevation
    0.78
    Altitude
    0.74
     mountains
    0.69
     mountain
    0.69
    DockStyle
    0.69
    manjaro
    0.68
     elevations
    0.68
    Activations Density 0.098%

    No Known Activations