© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 16316
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to criminal charges and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     investigating
    -0.42
     Evidence
    -0.42
     investigations
    -0.41
     Occur
    -0.40
     evidence
    -0.40
     events
    -0.39
     Crus
    -0.39
     alapján
    -0.39
     circumstantial
    -0.39
     Investigations
    -0.39
    POSITIVE LOGITS
    featureID
    1.04
    Obrázky
    0.81
    __':
    0.80
     GenerationType
    0.79
    __':
    0.79
    yntaxException
    0.77
     propOrder
    0.77
    bootstrapcdn
    0.77
    тьяна
    0.76
     كومونز
    0.75
    Activations Density 1.547%

    No Known Activations