© 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. 8849
    Prev
    Next
    INDEX
    Explanations

    elements related to account verification and confirmation processes

    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
     ujednoznacz
    -0.65
    rungsseite
    -0.60
    \{\\
    -0.59
    Tikang
    -0.59
    
    -0.57
    +#+#
    -0.56
     AssemblyVersion
    -0.56
    時候
    -0.55
    AndEndTag
    -0.55
    ########.
    -0.53
    POSITIVE LOGITS
     savo
    0.53
     свои
    0.53
     svoj
    0.47
     się
    0.46
     свою
    0.45
    сь
    0.44
    ся
    0.43
     svoje
    0.43
     zarówno
    0.41
     svo
    0.41
    Activations Density 0.028%

    No Known Activations