© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15157
    Prev
    Next
    INDEX
    Explanations

    references to violence and individuals named Matt

    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
    tagHelperRunner
    -0.83
    StreetMap
    -0.66
     Meksiku
    -0.62
    esthes
    -0.61
    ViewFeatures
    -0.60
     Stern
    -0.60
     ISNI
    -0.60
    COUVER
    -0.60
    OGND
    -0.59
    Stern
    -0.55
    POSITIVE LOGITS
     Matthew
    1.15
     Matt
    1.06
    Matthew
    1.05
    Matt
    0.97
     Katie
    0.77
    Katie
    0.76
    THEW
    0.76
    MATT
    0.74
    Dairy
    0.74
     Dairy
    0.70
    Activations Density 0.054%

    No Known Activations