Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 1001
    Prev
    Next
    INDEX
    Explanations

    expressions of complex emotional or interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Omg
    -0.46
    omg
    -0.41
     incrível
    -0.36
    死了
    -0.36
     incredible
    -0.35
    artigen
    -0.34
    Amazing
    -0.34
    Insane
    -0.33
    わかる
    -0.33
     amazing
    -0.33
    POSITIVE LOGITS
     plenty
    0.73
    plenty
    0.73
     mighty
    0.72
    addPreferredGap
    0.70
    /*
    0.69
    Plenty
    0.66
    なかな
    0.65
     awfully
    0.65
     decidedly
    0.65
    parsedMessage
    0.63
    Activations Density 0.481%

    No Known Activations