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. 17-GEMMASCOPE-RES-16K
    6. 5093
    Prev
    Next
    INDEX
    Explanations

    Japanese possessive or linking particles and expressions

    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
     of
    -0.68
     from
    -0.61
    お金
    -0.51
     exécut
    -0.49
    人數
    -0.49
     without
    -0.48
    人气
    -0.47
     tuttavia
    -0.47
     with
    -0.46
     refroid
    -0.46
    POSITIVE LOGITS
     '\\;'
    1.15
    IsMutable
    1.07
     мәкал
    1.04
    ".
    
    1.03
    }")
    
    1.02
    )";
    
    1.01
    )");
    
    0.98
    ")==
    0.98
    })->
    0.97
     estekak
    0.96
    Activations Density 0.026%

    No Known Activations