© 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. 23-GEMMASCOPE-RES-16K
    11. 9307
    Prev
    Next
    INDEX
    Explanations

    references to victims and their situations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.51
    <h1>
    -0.39
    Transcription
    -0.39
    ¿
    -0.36
    Purpose
    -0.35
    entran
    -0.34
    Welcome
    -0.34
    例文帳に追加
    -0.34
    ¡
    -0.33
     acc
    -0.33
    POSITIVE LOGITS
     Chwiliwch
    0.63
    原始内容存档于
    0.61
     CreateTagHelper
    0.58
     mijne
    0.57
    
    0.56
    WithMany
    0.54
     صوتيه
    0.53
    httphttps
    0.53
    rungsseite
    0.52
    帖最后由
    0.49
    Activations Density 2.005%

    No Known Activations