© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4650
    Prev
    Next
    INDEX
    Explanations

    references to communication and speech-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.57
    inWeight
    -0.51
    __(/*!
    -0.48
    mbggenerated
    -0.48
     ब्रेकडाउन
    -0.47
    الإنجليزية
    -0.46
     كومونز
    -0.44
    
    -0.44
    yelitis
    -0.44
     Савезне
    -0.43
    POSITIVE LOGITS
     speech
    0.98
     Speech
    0.88
     voice
    0.83
     utterance
    0.83
    Speech
    0.82
     verbal
    0.81
     spoken
    0.79
    peech
    0.74
     SPEECH
    0.73
    speech
    0.72
    Activations Density 0.627%

    No Known Activations