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. 21-GEMMASCOPE-RES-16K
    6. 14200
    Prev
    Next
    INDEX
    Explanations

    phrases related to service guarantees and promotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuspendLayout
    -0.48
     насељу
    -0.46
    üf
    -0.45
    MENAFN
    -0.44
    うる
    -0.42
    AutoScaleMode
    -0.41
     lieber
    -0.41
    ▾
    -0.41
    例句
    -0.41
    ucht
    -0.40
    POSITIVE LOGITS
     free
    3.34
    free
    2.93
     FREE
    2.80
    FREE
    2.70
    Free
    2.66
     Free
    2.65
     gratis
    2.48
    免费
    2.18
     gratuitement
    2.15
     gratuite
    2.13
    Activations Density 0.217%

    No Known Activations