© 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. 8425
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters

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

    years in the format "20XX", particularly focusing on recent years like 2017-2019.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @yangmungi
    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
    ="@+
    -0.59
     thirteen
    -0.58
     Thirteen
    -0.56
     विश्वसनीयता
    -0.56
     sixth
    -0.56
    featureID
    -0.54
     fifth
    -0.54
     ninth
    -0.53
     fourth
    -0.52
     triple
    -0.52
    POSITIVE LOGITS
    2
    2.16
    ２
    1.19
    ২
    1.04
     Twenty
    1.02
     twenty
    1.02
    २
    0.99
    ۲
    0.98
     ٢
    0.95
    ٢
    0.91
     TWENTY
    0.90
    Activations Density 6.261%

    No Known Activations