© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 3776
    Prev
    Next
    INDEX
    Explanations

    events or actions involving violence and aggression

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

    Preceding verbs followed by "him"

    np_acts-logits-general · gemini-2.0-flash

    actions toward him

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    they
    -0.76
    he
    -0.75
    she
    -0.64
    his
    -0.64
     they
    -0.62
     그의
    -0.60
     kanyang
    -0.60
     вони
    -0.60
     istrinya
    -0.57
     hendes
    -0.57
    POSITIVE LOGITS
     him
    3.36
    him
    1.90
     honom
    1.53
     ihn
    1.40
     ihm
    1.28
     lui
    1.27
     Him
    1.25
     HIM
    1.15
    Him
    1.13
     them
    1.09
    Activations Density 0.288%

    No Known Activations