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. 14-GEMMASCOPE-RES-16K
    6. 7580
    Prev
    Next
    INDEX
    Explanations

    terms related to participation in studies and the associated requirements or incentives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queous
    -0.53
     referenties
    -0.51
    +#+#
    -0.50
     Marconi
    -0.49
     Koy
    -0.48
    osphere
    -0.48
     FormData
    -0.47
    urtles
    -0.47
    følgelig
    -0.47
     ?>/
    -0.46
    POSITIVE LOGITS
     unless
    1.23
    unless
    1.09
     except
    1.00
     Unless
    0.98
     kecuali
    0.97
    Unless
    0.97
     melainkan
    0.85
     anymore
    0.84
     nor
    0.82
    除非
    0.82
    Activations Density 0.815%

    No Known Activations