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. 9-GEMMASCOPE-RES-16K
    6. 9360
    Prev
    Next
    INDEX
    Explanations

    references to siblings and family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CLR
    -0.83
    })));
    -0.82
    isticated
    -0.80
     dci
    -0.79
     ECS
    -0.75
     Lupin
    -0.75
     glan
    -0.74
     virt
    -0.74
    DispatchToProps
    -0.73
     Gandalf
    -0.72
    POSITIVE LOGITS
     brother
    1.72
     BROTHER
    1.71
     brothers
    1.66
    brother
    1.61
    Brother
    1.52
     Brother
    1.51
     Brothers
    1.43
    brothers
    1.40
     sister
    1.35
    Brothers
    1.30
    Activations Density 0.045%

    No Known Activations