Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 13117
    Prev
    Next
    INDEX
    Explanations

    verbs and actions used in various contexts, particularly in communication and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zostało
    -0.65
     zostanie
    -0.59
    σουμε
    -0.58
     became
    -0.56
     został
    -0.53
     zostały
    -0.53
    σετε
    -0.50
     została
    -0.50
     become
    -0.49
    ed
    -0.46
    POSITIVE LOGITS
     مرئيه
    1.13
     nahilalakip
    1.12
    UnusedPrivate
    1.05
    fjspx
    0.98
    (!__
    0.96
    InjectAttribute
    0.95
    expandindo
    0.94
    parsedMessage
    0.92
     سكانية
    0.90
     TestBed
    0.85
    Activations Density 0.036%

    No Known Activations