© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8738
    Prev
    Next
    INDEX
    Explanations

    occurrences of technical or system-level error codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    <unused43>
    -0.67
    <unused51>
    -0.67
    <pad>
    -0.67
    <unused52>
    -0.67
    <unused41>
    -0.67
    <unused47>
    -0.66
    <unused79>
    -0.66
    <unused28>
    -0.66
    [@BOS@]
    -0.66
    <unused14>
    -0.66
    POSITIVE LOGITS
    ↵↵
    0.45
    -
    0.45
    ,
    0.42
    WriteTagHelper
    0.38
     Отечественной
    0.37
    //
    0.37
    fromnode
    0.36
     (
    0.34
     en
    0.34
    /*
    0.33
    Activations Density 0.761%

    No Known Activations