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. 8-GEMMASCOPE-RES-16K
    6. 7770
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or periods in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.48
    えもん
    -0.47
    esseract
    -0.45
    стан
    -0.45
    IVOS
    -0.44
     pañ
    -0.44
    ies
    -0.44
    ้ง
    -0.43
    вости
    -0.43
    styleType
    -0.43
    POSITIVE LOGITS
     AssemblyTitle
    0.93
    +#+#
    0.79
     utafitiHapana
    0.72
    ]")]
    0.70
    IBOutlet
    0.69
     وتسجيلات
    0.68
    Autoritní
    0.68
    SBATCH
    0.66
     pylint
    0.66
    بوابة
    0.66
    Activations Density 0.010%

    No Known Activations