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 - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65821
    Prev
    Next
    INDEX
    Explanations

    references to online video channels and links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cgi
    -0.50
    Tweet
    -0.45
    FunctionFlags
    -0.44
    ++];
    -0.42
    ഘ
    -0.41
    blico
    -0.41
     يتيمه
    -0.41
     المعيارى
    -0.41
    fate
    -0.40
    mbler
    -0.40
    POSITIVE LOGITS
     channel
    1.82
     channels
    1.50
    channel
    1.44
     Channel
    1.41
     CHANNEL
    1.34
     canale
    1.30
    Channel
    1.27
     Channels
    1.24
    CHANNEL
    1.20
    channels
    1.20
    Activations Density 0.012%

    No Known Activations