© 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. 30-GEMMASCOPE-RES-16K
    11. 7936
    Prev
    Next
    INDEX
    Explanations

    connections and interactions between individuals

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

    knowing, getting to know, or being acquainted

    np_acts-logits-general · gemini-2.0-flash

    acquaintance or knowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.50
    IBOutlet
    -0.50
    ፩
    -0.50
     kasarigan
    -0.49
    RegistryLite
    -0.47
    ValueStyle
    -0.45
    Diwedd
    -0.45
    Rujuakan
    -0.43
    SharedDtor
    -0.42
    RTDA
    -0.42
    POSITIVE LOGITS
     acquaintance
    1.16
     conhecer
    1.15
     conocer
    1.15
     mengenal
    1.11
     acquainted
    1.07
     conhe
    1.06
     kenal
    1.05
     kennen
    1.03
     conoce
    1.02
     know
    1.01
    Activations Density 0.206%

    No Known Activations