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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5982
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to statistical methodologies and data analysis

    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
     ved
    -0.26
     ad
    -0.25
     per
    -0.24
     alam
    -0.24
     pot
    -0.24
    ラ
    -0.24
     va
    -0.22
     Sk
    -0.22
     end
    -0.22
    ab
    -0.21
    POSITIVE LOGITS
     onPostExecute
    0.69
    ConstraintMaker
    0.67
    majánló
    0.66
     ſind
    0.66
    ſelf
    0.66
    AndEndTag
    0.66
     ſever
    0.65
    ésult
    0.64
     Infór
    0.63
     queſta
    0.63
    Activations Density 0.960%

    No Known Activations