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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5744
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and quantitative data related to research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.76
     raiſ
    -0.65
     imagui
    -0.65
     fashiola
    -0.64
    fjspx
    -0.63
     ſta
    -0.63
    ロウィン
    -0.60
     queſta
    -0.60
    ſcher
    -0.60
     témoig
    -0.60
    POSITIVE LOGITS
     ancillary
    0.31
    err
    0.28
    tre
    0.27
     atom
    0.27
    webElementXpaths
    0.27
     spur
    0.27
     fly
    0.26
     m
    0.26
    TS
    0.26
     AP
    0.26
    Activations Density 3.277%

    No Known Activations