© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2939
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological processes and improvements

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

    phrases indicating potential and improvement in processes or technologies

    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
    +:+
    -0.62
    ómica
    -0.57
     Roskov
    -0.53
     omo
    -0.53
    InputBorder
    -0.53
    клопе
    -0.52
    ]--;
    -0.50
    clable
    -0.49
    Gön
    -0.48
     entsteht
    -0.47
    POSITIVE LOGITS
     improve
    1.04
     beef
    0.92
     enhance
    0.92
    AccessorTable
    0.91
     amp
    0.88
     spice
    0.85
    beef
    0.85
     increase
    0.82
     expand
    0.77
    improve
    0.77
    Activations Density 0.549%

    No Known Activations