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. 1-GEMMASCOPE-RES-16K
    6. 7150
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to law enforcement and its functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Phal
    -0.65
     useAppContext
    -0.64
    复制代码
    -0.61
     يتيمه
    -0.61
     Wikime
    -0.60
    lana
    -0.60
    ).</
    -0.60
    ')")
    -0.60
    esModule
    -0.59
    ]',
    -0.59
    POSITIVE LOGITS
     enforcement
    1.12
    enforcement
    0.93
     Enforcement
    0.92
    tel
    0.83
     enforce
    0.76
     enforcing
    0.74
    Enforcement
    0.73
    %%
    0.72
     cabinet
    0.63
    counts
    0.62
    Activations Density 0.119%

    No Known Activations