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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6296
    Prev
    Next
    INDEX
    Explanations

    specific references to communication and user interactions within a digital context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    question marks and the words surrounding them, particularly in interrogative sentences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.59
    GEBURTS
    -0.57
    :+:
    -0.54
     calendriers
    -0.54
     Anſ
    -0.49
     franz
    -0.48
     ſte
    -0.46
     TRAFFIC
    -0.46
    irut
    -0.46
    
    -0.46
    POSITIVE LOGITS
    \{\\
    0.54
    uxxxx
    0.43
    توض
    0.41
    pulseira
    0.40
    corazón
    0.40
     lisäksi
    0.40
    deutig
    0.39
    ditto
    0.39
    numerusform
    0.39
    ंदीखरीदारी
    0.38
    Activations Density 0.739%

    No Known Activations