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. 3-GEMMASCOPE-RES-16K
    6. 12700
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks, particularly those indicating uncertainty or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invokevirtual
    -0.57
    .
    -0.47
    softc
    -0.46
    Lud
    -0.45
     ver
    -0.44
     I
    -0.44
     (
    -0.44
     Stä
    -0.43
     Lud
    -0.42
    likopter
    -0.42
    POSITIVE LOGITS
     ?
    2.18
     ?'
    2.06
     ??
    2.04
     ???
    2.04
    .?
    1.95
    ??????
    1.93
    -?
    1.92
     ????
    1.90
     '?
    1.89
    %?
    1.88
    Activations Density 0.101%

    No Known Activations