© 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. 11-GEMMASCOPE-RES-16K
    6. 1604
    Prev
    Next
    INDEX
    Explanations

    references to the variable 'j' and its calculations or assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setAll
    -0.64
     możliwe
    -0.63
     Toten
    -0.63
     måte
    -0.60
     shape
    -0.56
    vábbi
    -0.56
    OutOfRange
    -0.55
    Thank
    -0.55
     contrat
    -0.54
    ėl
    -0.54
    POSITIVE LOGITS
     Jamb
    1.24
     JAS
    1.16
     Jy
    1.14
     jLabel
    1.13
     jc
    1.11
     jy
    1.11
     Jot
    1.11
     Jes
    1.10
    Jem
    1.10
     Jays
    1.10
    Activations Density 0.690%

    No Known Activations