© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 14654
    Prev
    Next
    INDEX
    Explanations

    references to the left side or left alignment in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.88
    getInstance
    -0.87
    $_['
    -0.87
     <<<<<<<<<<<<<<
    -0.84
    TypedDataSet
    -0.83
    Personensuche
    -0.82
    +:+
    -0.81
     propOrder
    -0.81
    __':
    
    -0.81
    WireFormatLite
    -0.80
    POSITIVE LOGITS
     left
    2.05
     Left
    1.98
    left
    1.93
    Left
    1.91
     LEFT
    1.77
    LEFT
    1.70
    getLeft
    1.44
    Lef
    1.31
    setLeft
    1.30
     Lef
    1.30
    Activations Density 0.067%

    No Known Activations