© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 325
    Prev
    Next
    INDEX
    Explanations

    modality and probability indicators, such as words suggesting potential outcomes or possibilities

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

    modal verbs and possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doigt
    -0.37
     conocemos
    -0.35
     conoce
    -0.35
     conoc
    -0.35
     conhece
    -0.33
     possu
    -0.32
     przecież
    -0.31
    inverno
    -0.30
     Bedeutung
    -0.30
     conhecer
    -0.30
    POSITIVE LOGITS
    DockStyle
    0.67
     ſind
    0.66
    AnchorStyles
    0.63
    帖最后由
    0.63
    RetentionPolicy
    0.63
     فريبيس
    0.60
     WebDriverWait
    0.59
    afficheront
    0.58
     encre
    0.58
    posedge
    0.56
    Activations Density 0.153%

    No Known Activations