© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 985
    Prev
    Next
    INDEX
    Explanations

    references to siblings and family relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    harusnya
    -0.81
    awtextra
    -0.73
     AssemblyCulture
    -0.70
    })));
    -0.66
    setContentView
    -0.64
    GeneratedValue
    -0.64
     ansi
    -0.63
     setuptools
    -0.63
     XNUMX
    -0.62
     bodyParser
    -0.61
    POSITIVE LOGITS
     sister
    2.25
     sisters
    2.11
     brother
    2.06
     Sister
    1.98
    sister
    1.96
     brothers
    1.92
    Sister
    1.92
    brother
    1.88
     Brother
    1.81
     BROTHER
    1.81
    Activations Density 0.102%

    No Known Activations