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. 11-GEMMASCOPE-RES-16K
    6. 7030
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to parenthood and childbearing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चीज़ों
    -0.65
    الإنجليزية
    -0.62
    abstractmethod
    -0.57
    aarrggbb
    -0.57
    })));
    -0.56
    IsMutable
    -0.56
    StructEnd
    -0.54
    FunctionFlags
    -0.53
    InstrumentedTest
    -0.52
    SourceChecksum
    -0.51
    POSITIVE LOGITS
     setuptools
    0.58
     للمعارف
    0.58
    nocześnie
    0.58
     anywhere
    0.55
    anywhere
    0.53
     arrivo
    0.53
     newState
    0.51
     estimés
    0.51
     vacanza
    0.51
    ifax
    0.50
    Activations Density 0.473%

    No Known Activations