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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4194
    Prev
    Next
    INDEX
    Explanations

    sentences that convey conditional reasoning or personal insights

    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
     skall
    -0.78
     muß
    -0.75
     läßt
    -0.74
    ・・・・・
    -0.63
     denominado
    -0.61
    であるが
    -0.58
     lecz
    -0.57
     mußte
    -0.57
     yoktur
    -0.56
     آنان
    -0.56
    POSITIVE LOGITS
     shitty
    1.08
     tryna
    1.08
     tbh
    1.07
     weirdly
    1.06
     whatnot
    1.04
     idk
    1.04
     fucked
    1.02
     goddamn
    1.00
     lemme
    0.98
     kinda
    0.98
    Activations Density 1.698%

    No Known Activations