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-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2449
    Prev
    Next
    INDEX
    Explanations

    dependencies and issues related to infrastructure and service delivery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </thead>
    -0.33
     potongan
    -0.31
     calendriers
    -0.31
    .*")]
    -0.30
     maioria
    -0.29
    esModule
    -0.29
     ciclo
    -0.29
    PointerException
    -0.28
     sø
    -0.28
    InteropServices
    -0.28
    POSITIVE LOGITS
     overcrowded
    0.84
     Capacity
    0.83
    capacity
    0.82
     capacity
    0.82
     overcrowding
    0.80
     Overflow
    0.79
     overloaded
    0.79
     overload
    0.79
    Capacity
    0.78
     Overload
    0.73
    Activations Density 0.486%

    No Known Activations