© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 289
    Prev
    Next
    INDEX
    Explanations

    reference to legal defenses and strategies regarding material possession and removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases using "as" to indicate manner or degree, particularly in comparative or descriptive contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.48
     مرئيه
    -0.39
    URLException
    -0.37
     soudain
    -0.37
     suddenly
    -0.36
     plötzlich
    -0.36
    Suddenly
    -0.36
    NOPQRST
    -0.35
    iface
    -0.35
    大変
    -0.35
    POSITIVE LOGITS
     möglichst
    1.86
    尽可能
    1.68
    できるだけ
    1.57
    なるべく
    1.45
     максимально
    1.38
    尽量
    1.31
     mümkün
    1.24
    儘
    1.24
    盡
    1.20
     maximize
    1.18
    Activations Density 0.814%

    No Known Activations