© 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. 8-GEMMASCOPE-RES-16K
    11. 13688
    Prev
    Next
    INDEX
    Explanations

    conjunctive phrases indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lyd
    -0.70
     Rite
    -0.69
     Lend
    -0.69
     }}">
    -0.68
    ziesz
    -0.68
    Rite
    -0.67
     Frm
    -0.66
    ———-
    -0.65
     Alb
    -0.64
     Zink
    -0.63
    POSITIVE LOGITS
    theless
    1.17
     however
    1.08
     However
    1.07
    however
    1.06
    +#+
    1.02
     Porém
    0.96
    However
    0.95
    unhofer
    0.89
     Cependant
    0.89
    HostException
    0.88
    Activations Density 0.070%

    No Known Activations