© 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. 37-GEMMASCOPE-RES-16K
    11. 8144
    Prev
    Next
    INDEX
    Explanations

    references to speech-related difficulties or abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzleHttp
    -0.51
     CreateTagHelper
    -0.48
    HtmlAttribute
    -0.48
    Sucesor
    -0.46
    WithMany
    -0.44
    migrationBuilder
    -0.44
    PreferredItem
    -0.42
     StatefulWidget
    -0.41
    SequentialGroup
    -0.40
     विश्वसनीयता
    -0.40
    POSITIVE LOGITS
     words
    1.60
     speech
    1.52
     phrases
    1.41
     utterance
    1.35
     utterances
    1.33
     uttered
    1.32
     sentences
    1.30
     spoken
    1.28
     Words
    1.27
    Words
    1.25
    Activations Density 0.829%

    No Known Activations