© 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. 17-GEMMASCOPE-RES-16K
    6. 1406
    Prev
    Next
    INDEX
    Explanations

    certain sequences of underscored characters in a formatted data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    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
    -0.98
    MOUTH
    -0.93
    entityManager
    -0.92
     Teb
    -0.84
    ghed
    -0.83
     GenerationType
    -0.83
     ***!
    -0.83
    发表于
    -0.83
    mappedBy
    -0.82
    errHandler
    -0.81
    POSITIVE LOGITS
          
    0.95
    									
    0.73
         
    0.66
    сихо
    0.64
    )),
    0.63
     coun
    0.60
    o
    0.60
    とても
    0.60
     Dulles
    0.59
    ]),
    0.59
    Activations Density 0.135%

    No Known Activations