Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5004
    Prev
    Next
    INDEX
    Explanations

    references to supplementary material in scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Komun
    -0.51
    +:+
    -0.49
    tagHelperRunner
    -0.47
    MemoryWarning
    -0.47
    astéro
    -0.47
    !*\
    -0.46
    })=
    -0.44
    THON
    -0.44
    èrement
    -0.44
    ayı
    -0.44
    POSITIVE LOGITS
     الدولى
    0.63
     utafitiHapana
    0.62
    Skocz
    0.58
    archiviato
    0.55
    LVANIA
    0.55
    
    0.54
    liau
    0.53
    ropractor
    0.52
     المعرف
    0.51
    jfree
    0.51
    Activations Density 0.901%

    No Known Activations