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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 2164
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting elements typically associated with mathematical or coding expressions

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

    Text enclosed in brackets

    np_acts-logits-general · gemini-2.0-flash

    Q

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FileDialog
    -0.51
     theater
    -0.50
     createSlice
    -0.49
     Theaters
    -0.49
    elfth
    -0.49
     resourceCulture
    -0.49
     ModelExpression
    -0.48
     unknownFields
    -0.48
    JsonKey
    -0.48
     Theater
    -0.47
    POSITIVE LOGITS
    Lugar
    0.56
    <eos>
    0.55
    انيف
    0.54
     cardiaque
    0.52
    })).
    0.51
    }))
    
    0.51
    onAttach
    0.50
    shafen
    0.50
     gerichtet
    0.50
    ]")]
    0.49
    Activations Density 0.845%

    No Known Activations