© 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. 25-GEMMASCOPE-RES-16K
    6. 11078
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events, particularly associated with movements or parties

    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
    BoxShadow
    -0.59
    րջ
    -0.57
    queryInterface
    -0.56
    #+#
    -0.55
    inquirer
    -0.55
    ритори
    -0.53
    CreateIndex
    -0.52
     NDC
    -0.51
    scryfall
    -0.51
    SPD
    -0.50
    POSITIVE LOGITS
     conservative
    1.23
     conservatism
    1.15
     conservatives
    1.11
    conservative
    1.06
    conserv
    0.96
     CONSERV
    0.93
     Conserv
    0.91
     Tea
    0.90
     Conservative
    0.90
    Conserv
    0.90
    Activations Density 0.514%

    No Known Activations