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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8453
    Prev
    Next
    INDEX
    Explanations

    code-related identifiers and structural elements in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ListItemIcon
    -0.45
    ValueStyle
    -0.44
     BioLib
    -0.40
     sèche
    -0.36
    NegativeButton
    -0.35
     Kontext
    -0.35
     Gedanke
    -0.34
    UrlResolution
    -0.33
     chromatography
    -0.33
     Stornier
    -0.33
    POSITIVE LOGITS
    +#+
    0.57
    mentaux
    0.54
    windowFixed
    0.53
    ArrowToggle
    0.52
    oredCriteria
    0.51
    WebMethod
    0.49
    ſelves
    0.48
    ſelf
    0.47
     nahilalakip
    0.46
     Савезне
    0.45
    Activations Density 1.095%

    No Known Activations