© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 11270
    Prev
    Next
    INDEX
    Explanations

    the presence and consistency of code-related elements and comments

    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
    oplayer
    -0.66
    ütü
    -0.58
     coppia
    -0.57
    Browsable
    -0.57
     lube
    -0.56
     desemple
    -0.56
     pursuance
    -0.55
     Maio
    -0.54
     escuro
    -0.54
     recevez
    -0.53
    POSITIVE LOGITS
     esternos
    0.73
     <<<<<<<<<<<<<<
    0.69
    anyahu
    0.68
     AssemblyCulture
    0.67
    principalColumn
    0.60
    الحياه
    0.59
    tagHelperRunner
    0.59
    WithIOException
    0.58
    ✨:
    0.58
     الرياضيه
    0.57
    Activations Density 0.665%

    No Known Activations