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. 36-GEMMASCOPE-RES-16K
    6. 11571
    Prev
    Next
    INDEX
    Explanations

    references to scheduled events or conditions concerning specific roles or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.65
     onPostExecute
    -0.58
    Autoritní
    -0.53
     autorytatywna
    -0.52
    RenderAtEndOf
    -0.51
    AddTagHelper
    -0.49
     Савезне
    -0.42
     Exactos
    -0.41
    RTEE
    -0.40
    interopRequire
    -0.39
    POSITIVE LOGITS
     start
    2.92
     starting
    2.86
     starts
    2.86
     beginning
    2.81
     begin
    2.72
     begins
    2.64
     started
    2.48
     Starting
    2.48
    starting
    2.45
     Starts
    2.45
    Activations Density 2.623%

    No Known Activations