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. 10-GEMMASCOPE-RES-16K
    6. 11094
    Prev
    Next
    INDEX
    Explanations

    terms related to legal contexts and ethical approvals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.85
    الحياه
    -0.58
    <strong>
    -0.44
     totiž
    -0.43
    <u>
    -0.42
     atacado
    -0.41
    ,
    -0.41
    agaimana
    -0.39
    <b>
    -0.39
    1
    -0.38
    POSITIVE LOGITS
    </h2>
    1.41
    </h4>
    1.34
     resourceCulture
    1.15
    StoryboardSegue
    1.12
    </u>
    1.11
    </strong>
    1.11
    AccessorTable
    1.09
    }$}
    1.09
     }}$}
    1.07
    </b>
    1.06
    Activations Density 1.334%

    No Known Activations