© 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. 10592
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals involved in criminal activities

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

    detailed descriptions of physical objects and their locations within vehicles or spaces.

    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
    XmlIgnore
    -0.42
     تانيه
    -0.41
    ictwa
    -0.39
    ruppen
    -0.37
     كومونز
    -0.37
    pulsera
    -0.35
    Hochspringen
    -0.35
    colgante
    -0.34
    Endereco
    -0.34
    anze
    -0.34
    POSITIVE LOGITS
     passenger
    1.30
     passengers
    1.24
     seat
    1.16
     seats
    1.09
    passenger
    1.05
     Passenger
    1.05
    Passenger
    1.04
     Passengers
    1.02
    seats
    1.01
    seat
    1.00
    Activations Density 0.312%

    No Known Activations