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. 4-GEMMASCOPE-RES-16K
    6. 11094
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.67
    ovac
    -0.60
    ruptedException
    -0.60
    hObject
    -0.57
     InputDecoration
    -0.50
    idable
    -0.50
    RegressionTest
    -0.50
     endfor
    -0.50
     IOException
    -0.49
     Дата
    -0.49
    POSITIVE LOGITS
    InputTagHelper
    0.63
    tangentMode
    0.60
    HtmlAttribute
    0.57
    NSYLVANIA
    0.57
     élu
    0.57
     utafitiHapana
    0.56
    PreferredItem
    0.54
     betweenstory
    0.53
     aimez
    0.52
     potřeb
    0.52
    Activations Density 0.091%

    No Known Activations