© 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. 15370
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that discuss possibilities or alternatives

    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
    بل
    -0.56
    ⎞
    -0.54
    pageX
    -0.53
     
    -0.51
    fetchAll
    -0.49
     SPIRIT
    -0.49
     Bland
    -0.49
     dokun
    -0.48
    ieR
    -0.47
    ［
    -0.47
    POSITIVE LOGITS
    onAttach
    0.84
     utafitiHapana
    0.72
    EndGlobalSection
    0.70
    новниш
    0.69
     Efq
    0.69
    loài
    0.67
    netbeans
    0.66
     Meksiku
    0.66
     entanto
    0.65
     dbo
    0.65
    Activations Density 0.091%

    No Known Activations