Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2615
    Prev
    Next
    INDEX
    Explanations

    punctuation and stylistic elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     références
    -0.65
    ScopeManager
    -0.55
    Références
    -0.47
    imetsu
    -0.44
     círculos
    -0.44
     rồi
    -0.43
     hóspedes
    -0.43
     référence
    -0.43
    axios
    -0.42
     Dever
    -0.42
    POSITIVE LOGITS
     overall
    0.89
    overall
    0.87
    Lovely
    0.81
     food
    0.81
     Overall
    0.81
     Lovely
    0.79
    Overall
    0.78
    nice
    0.76
     nice
    0.76
     Beautiful
    0.75
    Activations Density 0.043%

    No Known Activations