© 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. 25-GEMMASCOPE-RES-16K
    6. 4662
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "cat" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cancelar
    -0.53
    djangoproject
    -0.52
    didReceive
    -0.50
     calendriers
    -0.50
     ExecuteAsync
    -0.49
    rospy
    -0.49
    afterEach
    -0.49
     mergeFrom
    -0.48
    getTime
    -0.48
     solito
    -0.48
    POSITIVE LOGITS
     wireType
    0.79
    agory
    0.75
    pillar
    0.65
    hedrals
    0.63
    nip
    0.62
     متعلقه
    0.59
    ollectionView
    0.57
    IsContent
    0.56
    hedra
    0.55
    
    0.55
    Activations Density 0.216%

    No Known Activations