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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1811
    Prev
    Next
    INDEX
    Explanations

    concepts related to decision-making and action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    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
    SourceChecksum
    -0.88
    oredCriteria
    -0.77
    __((
    -0.69
     resourceCulture
    -0.67
    interopRequire
    -0.60
    VIAF
    -0.60
    utnant
    -0.60
    RTLD
    -0.59
     Վերցված
    -0.59
    Carriera
    -0.59
    POSITIVE LOGITS
    Geplaatst
    0.66
    فحه
    0.52
     Often
    0.47
    Often
    0.47
     tycker
    0.45
    tegen
    0.44
     usein
    0.43
     often
    0.42
    census
    0.41
    shutil
    0.41
    Activations Density 0.450%

    No Known Activations