© 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. 15-GEMMASCOPE-RES-16K
    6. 2087
    Prev
    Next
    INDEX
    Explanations

    contexts or phrases related to specific situations or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     derece
    -0.69
     AdapterView
    -0.68
     Chartres
    -0.68
     formel
    -0.68
    addEdge
    -0.66
    OnAdd
    -0.66
    ]--;
    -0.66
    }{*}{
    -0.66
    ειτουργ
    -0.65
    maxLines
    -0.65
    POSITIVE LOGITS
     situations
    1.74
     situation
    1.71
     Situations
    1.59
    situation
    1.54
     SITUATION
    1.49
     Situation
    1.45
    Situation
    1.41
    Situ
    1.37
    situ
    1.27
     circumstances
    1.23
    Activations Density 0.085%

    No Known Activations