Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 5402
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to value and contribution, particularly in the context of diverse communities and personal attributes

    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
    dojo
    -0.49
     impossível
    -0.49
     victimes
    -0.47
     inconn
    -0.46
    zzini
    -0.46
     cauza
    -0.46
     sehari
    -0.46
    anasia
    -0.45
    ่าน
    -0.45
     visitó
    -0.45
    POSITIVE LOGITS
     available
    0.73
     resources
    0.72
    kloped
    0.71
    ]")]
    0.69
    Available
    0.69
    SequentialGroup
    0.69
    ViewFeatures
    0.69
    EndGlobalSection
    0.68
     beschik
    0.68
    available
    0.67
    Activations Density 0.465%

    No Known Activations