© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12397
    Prev
    Next
    INDEX
    Explanations

    references to difficulties and problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CLIP
    -0.45
    Song
    -0.43
    Clip
    -0.42
    song
    -0.42
     teri
    -0.42
    tión
    -0.42
     jsPsych
    -0.42
    spitze
    -0.41
    dä
    -0.41
    Highway
    -0.41
    POSITIVE LOGITS
     troubles
    0.69
     encountered
    0.63
     experiencing
    0.61
     struggling
    0.60
     Troubles
    0.59
     trouble
    0.57
     troublesome
    0.55
     participating
    0.54
     prone
    0.53
    trouble
    0.53
    Activations Density 0.206%

    No Known Activations