© 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. 27-GEMMASCOPE-RES-16K
    6. 10153
    Prev
    Next
    INDEX
    Explanations

    expressions of cuteness and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BufferException
    -0.87
    oa̍t
    -0.54
     AssemblyTitle
    -0.53
    PMailer
    -0.47
     kvinna
    -0.44
     sumpay
    -0.44
    Попис
    -0.44
     AttributeSet
    -0.44
    TypedDataSet
    -0.43
     BorderSide
    -0.43
    POSITIVE LOGITS
     adorable
    1.63
     cute
    1.63
     Cute
    1.38
    Cute
    1.38
     Adorable
    1.37
     cutest
    1.30
    cute
    1.26
    Adorable
    1.23
     CUTE
    1.20
    adorable
    1.19
    Activations Density 0.155%

    No Known Activations