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. 12-GEMMASCOPE-RES-16K
    6. 3172
    Prev
    Next
    INDEX
    Explanations

    occurrences of function call syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    -1.00
    z
    -0.83
    el
    -0.81
    line
    -0.80
    a
    -0.78
    ment
    -0.76
    be
    -0.76
     Lacey
    -0.76
     Zie
    -0.76
    asa
    -0.75
    POSITIVE LOGITS
    ()");
    1.13
     Monfieur
    1.10
     للمعارف
    1.08
    }(),
    1.04
    ()',
    1.03
    )()
    1.01
     GIPHY
    0.99
    RetentionPolicy
    0.99
    }()
    0.98
    AsUp
    0.97
    Activations Density 0.092%

    No Known Activations