© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12678
    Prev
    Next
    INDEX
    Explanations

    discussion around historical women's strength and capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.72
    antMatchers
    -0.64
    aktery
    -0.58
    MultipartFile
    -0.53
    delaire
    -0.53
     leçon
    -0.51
    delli
    -0.49
     otomatig
    -0.48
    [:,:,
    -0.47
    Fns
    -0.46
    POSITIVE LOGITS
     speculation
    2.07
     hypothesis
    1.93
     guesses
    1.91
     suspicion
    1.89
     hypotheses
    1.86
     supposition
    1.85
     guess
    1.84
     suspicions
    1.83
     conjecture
    1.83
     guessed
    1.83
    Activations Density 0.747%

    No Known Activations