Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3845
    Prev
    Next
    INDEX
    Explanations

    references to female characters and their relationships in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     his
    -1.81
     himself
    -1.74
    his
    -1.49
    himself
    -1.39
    彼は
    -1.29
     he
    -1.25
    彼の
    -1.22
     seinem
    -1.19
     seinen
    -1.17
     seine
    -1.14
    POSITIVE LOGITS
     herself
    2.18
    herself
    1.65
     her
    1.20
     she
    1.14
    حياتها
    1.08
     ihrer
    1.07
     ihrem
    1.07
     acompañada
    1.02
     hennes
    1.01
     نفسها
    1.01
    Activations Density 0.187%

    No Known Activations