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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 35-GEMMASCOPE-RES-16K
    6. 7035
    Prev
    Next
    INDEX
    Explanations

    technical and logical constructs in programming or web contexts

    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
    -
    -1.15
    ‑
    -0.68
    ‐
    -0.65
    ־
    -0.59
    −
    -0.57
    ®-
    -0.56
    -
    -0.54
    –
    -0.52
    -​
    -0.48
    -\
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.57
    下载附件
    0.50
    دانشنامهٔ
    0.50
     صوتيه
    0.49
    лактика
    0.48
    PositiveButton
    0.47
    Geplaatst
    0.47
    पया
    0.45
    InputBorder
    0.45
     stanovnika
    0.45
    Activations Density 1.539%

    No Known Activations