Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 493
    Prev
    Next
    INDEX
    Explanations

    references to installation processes and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     creș
    -0.81
     papild
    -0.71
     ſch
    -0.69
     Wikiseite
    -0.69
     Majefty
    -0.66
     ſche
    -0.65
     întâ
    -0.65
     picioare
    -0.64
     aukš
    -0.63
     tsy
    -0.63
    POSITIVE LOGITS
     '@/
    0.83
     "..\..\
    0.83
    withOpacity
    0.83
    FailureListener
    0.81
    sizeCache
    0.80
    __':
    
    0.80
    rrggbb
    0.78
    '.$
    0.76
    SPJ
    0.76
    TypedDataSet
    0.75
    Activations Density 0.041%

    No Known Activations