© 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. 861
    Prev
    Next
    INDEX
    Explanations

    programming language constructs related to data types

    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
     Anſ
    -1.05
     Theſe
    -1.01
     Reſ
    -0.98
     doubtnut
    -0.97
     Jefus
    -0.97
     ſever
    -0.94
     leaſt
    -0.93
     AppBar
    -0.91
     ſhall
    -0.91
     Monfieur
    -0.91
    POSITIVE LOGITS
    Type
    1.77
     Type
    1.69
    TYPE
    1.43
     TYPE
    1.41
    type
    1.34
    getType
    1.32
     type
    1.32
     types
    1.30
     getType
    1.28
    types
    1.26
    Activations Density 0.140%

    No Known Activations