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. 1-GEMMASCOPE-RES-16K
    6. 6054
    Prev
    Next
    INDEX
    Explanations

    instances of the word "guilty" and related terms indicating a conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.58
     rayos
    -0.55
    çalves
    -0.54
     decorar
    -0.54
     puntata
    -0.53
    
    -0.53
    EClass
    -0.52
    WebpackPlugin
    -0.51
     adorned
    -0.51
    膜
    -0.51
    POSITIVE LOGITS
     interim
    0.69
    theless
    0.69
     poffible
    0.66
     shield
    0.65
    Activités
    0.65
     pleaſure
    0.64
    ppled
    0.64
     Anſ
    0.61
     Monfieur
    0.61
     guilty
    0.60
    Activations Density 0.186%

    No Known Activations