© 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. 9-GEMMASCOPE-RES-16K
    11. 9534
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to making correct choices or using appropriate tools and strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -|-
    -0.40
    毎
    -0.38
     commonly
    -0.36
    fitrión
    -0.35
    ẵ
    -0.35
     []*
    -0.34
    digd
    -0.34
    Vidite
    -0.34
     onStop
    -0.34
    فته
    -0.33
    POSITIVE LOGITS
     giusta
    1.02
     wrong
    1.00
     richtigen
    0.99
     correct
    0.98
    Wrong
    0.95
     Wrong
    0.95
     richtige
    0.94
    wrong
    0.92
    Appropriate
    0.91
     appropriate
    0.90
    Activations Density 0.224%

    No Known Activations