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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12783
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structure elements

    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
     defaultstate
    -0.73
     betweenstory
    -0.56
    tvguidetime
    -0.55
    Personensuche
    -0.51
     صوتيه
    -0.50
    StoryboardSegue
    -0.50
    ፩
    -0.50
    verifyException
    -0.48
    WriteTagHelper
    -0.48
     Мексичка
    -0.48
    POSITIVE LOGITS
    <eos>
    0.50
    copg
    0.42
    Ahead
    0.41
    Dougall
    0.39
    neſs
    0.38
    Senti
    0.38
     reportedly
    0.38
    Revelation
    0.38
    stdc
    0.37
     ifølge
    0.37
    Activations Density 0.019%

    No Known Activations