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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7874
    Prev
    Next
    INDEX
    Explanations

    instances of the term "academic."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.45
     histórias
    -0.44
    Cechy
    -0.43
    ftagPool
    -0.40
    XmlAccessorType
    -0.39
     cassa
    -0.39
     dankbar
    -0.39
    FACTS
    -0.39
    型号
    -0.38
    jednoc
    -0.38
    POSITIVE LOGITS
    ians
    0.83
    ian
    0.60
     achievement
    0.56
     Achievement
    0.56
    期刊论文
    0.53
    Achievement
    0.52
    achievement
    0.52
     dishonesty
    0.48
    copg
    0.47
     rigor
    0.47
    Activations Density 0.126%

    No Known Activations