© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12132
    Prev
    Next
    INDEX
    Explanations

    URLs and web-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    AnchorStyles
    -0.58
    AddTagHelper
    -0.57
    enterOuterAlt
    -0.56
     autorytatywna
    -0.53
     Majefty
    -0.52
    COUVER
    -0.52
    createStatement
    -0.51
    tagHelperRunner
    -0.51
     PeEnEo
    -0.51
    ſelf
    -0.50
    POSITIVE LOGITS
     blog
    0.77
    blog
    0.70
     blogging
    0.67
     Blog
    0.67
    Blog
    0.66
     blogs
    0.63
     Blogging
    0.60
     blogger
    0.57
     postings
    0.54
    BLOG
    0.54
    Activations Density 0.235%

    No Known Activations