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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 2245
    Prev
    Next
    INDEX
    Explanations

    terms related to processes and actions of degradation or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before suffixes such as "-ize", "-ised", "-ishes", "-zing"

    np_acts-logits-general · gemini-2.0-flash

    forming words from roots and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ized
    -1.87
    ed
    -1.40
    ened
    -1.34
    ated
    -1.32
    ENED
    -0.95
    wards
    -0.94
    ged
    -0.90
    ED
    -0.88
    ured
    -0.86
    ulated
    -0.85
    POSITIVE LOGITS
    发表于
    0.62
    ddot
    0.53
     onResponse
    0.52
     TestBed
    0.52
    脚注の使い方
    0.52
    tonsoft
    0.51
     EventArgs
    0.51
    }))
    
    0.50
    tling
    0.50
    )}
    
    0.49
    Activations Density 0.351%

    No Known Activations