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. 7-GEMMASCOPE-RES-16K
    6. 6172
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Al" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -1.04
    ]")]
    -0.88
     Dü
    -0.81
    BibitemShut
    -0.80
    Hochspringen
    -0.79
    CppMethod
    -0.77
     Cott
    -0.77
    +#+#
    -0.76
    shadowOffset
    -0.74
    CopyWith
    -0.73
    POSITIVE LOGITS
     Al
    1.89
    Al
    1.79
     AL
    1.48
     al
    1.43
    AL
    1.17
    al
    1.11
    アル
    1.09
     Albrecht
    1.09
     Albright
    1.02
     aluminum
    0.99
    Activations Density 0.057%

    No Known Activations