© 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. 12-GEMMASCOPE-RES-16K
    6. 16259
    Prev
    Next
    INDEX
    Explanations

    tags related to navigation elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hiv
    -0.68
    Clara
    -0.67
    lccc
    -0.66
    Ciri
    -0.66
     Brandenburg
    -0.65
     Kyo
    -0.65
    /**
    -0.64
     SPARK
    -0.63
     Palestine
    -0.63
     Kome
    -0.63
    POSITIVE LOGITS
    ul
    1.16
     Ul
    0.89
     عليكم
    0.88
    UL
    0.85
     ul
    0.84
     Ulrich
    0.82
     Dumont
    0.80
    Ul
    0.78
    ulx
    0.76
     Eul
    0.75
    Activations Density 0.045%

    No Known Activations