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. 14-GEMMASCOPE-RES-16K
    6. 10512
    Prev
    Next
    INDEX
    Explanations

    elements related to function parameters and error handling in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mappedBy
    -0.53
    脚注の使い方
    -0.49
    ख्य
    -0.49
    ifiquement
    -0.49
     елның
    -0.48
    stand
    -0.48
     Bohn
    -0.48
    तान
    -0.48
    psin
    -0.48
    ecz
    -0.47
    POSITIVE LOGITS
    tagHelper
    0.80
    apimachinery
    0.74
    gonic
    0.68
     kasarigan
    0.65
     typelib
    0.65
    AttributeSet
    0.65
    </h6>
    0.64
    httphttps
    0.64
    PMailer
    0.63
    }")]
    0.61
    Activations Density 0.069%

    No Known Activations