© 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. 30-GEMMASCOPE-RES-16K
    6. 12759
    Prev
    Next
    INDEX
    Explanations

    positional phrases related to parts of objects or body

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

    Follows the word "of" or "a"

    np_acts-logits-general · gemini-2.0-flash

    opening of a

    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
     uſe
    -0.43
     Reſ
    -0.43
     canin
    -0.43
     nakalista
    -0.43
     catar
    -0.42
     Anſ
    -0.42
    delwed
    -0.41
    consulté
    -0.40
     Glanz
    -0.40
     Unemployment
    -0.40
    POSITIVE LOGITS
    CloseOperation
    0.57
    principalTable
    0.51
    DockStyle
    0.45
    󠁣
    0.44
     postIndex
    0.41
    Distribuzione
    0.40
    某
    0.40
    retudo
    0.39
    withIdentifier
    0.39
     unsuspecting
    0.38
    Activations Density 0.755%

    No Known Activations