© 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. 33-GEMMASCOPE-RES-16K
    11. 7747
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries regarding possibility and necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     almost
    -0.72
     hampir
    -0.67
     quase
    -0.66
     neither
    -0.65
     rất
    -0.64
    almost
    -0.63
    幾乎
    -0.63
    几乎
    -0.61
     почти
    -0.61
     بسیار
    -0.60
    POSITIVE LOGITS
     jemals
    1.09
     ever
    0.94
     any
    0.94
     überhaupt
    0.93
     quelconque
    0.90
     anything
    0.88
     anymore
    0.87
     siquiera
    0.83
    有任何
    0.80
     EVER
    0.76
    Activations Density 0.708%

    No Known Activations