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. 10-GEMMASCOPE-RES-16K
    6. 5294
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to software licensing and liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.59
     last
    -0.56
    <eos>
    -0.52
    ->
    -0.51
     Z
    -0.51
     si
    -0.51
     l
    -0.50
    '
    -0.49
     "
    -0.49
     in
    -0.49
    POSITIVE LOGITS
    ISupport
    6.64
     myſelf
    1.52
     CreateTagHelper
    1.51
     itſelf
    1.42
     ModelExpression
    1.42
     ―――――
    1.41
     AssemblyTitle
    1.41
     reaſon
    1.40
    GEBURTSDATUM
    1.39
     poffible
    1.34
    Activations Density 0.006%

    No Known Activations