© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 1855
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief or skepticism

    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
     sal
    -0.63
     referenties
    -0.59
    WireFormatLite
    -0.59
    Hayden
    -0.58
    яс
    -0.58
    sal
    -0.55
     Bru
    -0.55
    érias
    -0.54
     kronor
    -0.53
    ,@
    -0.53
    POSITIVE LOGITS
     Cannot
    1.13
     CANT
    1.08
     Cant
    1.06
    Cant
    1.00
     CANNOT
    1.00
     cant
    0.96
     cannot
    0.95
    cannot
    0.95
    Cannot
    0.94
     canst
    0.91
    Activations Density 0.110%

    No Known Activations