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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7593
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and conjunctions signaling communication or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.70
    httphttps
    -0.62
    AddTagHelper
    -0.62
    MessageTagHelper
    -0.61
    AndEndTag
    -0.60
    OGND
    -0.58
     Infórmanos
    -0.57
    MLLoader
    -0.56
    principalTable
    -0.55
     Chwiliwch
    -0.55
    POSITIVE LOGITS
    Whilst
    0.85
     Whilst
    0.82
    £
    0.69
     £
    0.68
     whilst
    0.67
     ausser
    0.59
     recognising
    0.58
     Recogn
    0.58
     marvellous
    0.58
     realising
    0.57
    Activations Density 0.400%

    No Known Activations