© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10048
    Prev
    Next
    INDEX
    Explanations

    statements and questions that express uncertainty or concerns regarding availability and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skak
    -0.40
    meanor
    -0.35
    ukone
    -0.34
    kez
    -0.34
    getOutputStream
    -0.34
     überhaupt
    -0.34
     delirium
    -0.34
    AddWithValue
    -0.33
    laient
    -0.33
     PUSTAKA
    -0.33
    POSITIVE LOGITS
     unfortunately
    3.63
     sadly
    3.33
    unfortunately
    3.20
    Unfortunately
    3.05
     Unfortunately
    3.02
     malheureusement
    2.92
    Sadly
    2.92
     Sadly
    2.91
     purtroppo
    2.89
     niestety
    2.81
    Activations Density 0.600%

    No Known Activations