© 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. 21-GEMMASCOPE-RES-16K
    6. 8046
    Prev
    Next
    INDEX
    Explanations

    the word "ma" and its variations, suggesting it is looking for references to a mother figure or similar concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.70
    contentLoaded
    -0.67
    FieldBuilder
    -0.60
    mobileqq
    -0.60
    COUVER
    -0.58
    mybatisplus
    -0.58
    mpions
    -0.57
     referenties
    -0.57
    Източници
    -0.57
    Esa
    -0.56
    POSITIVE LOGITS
    ConstraintMaker
    0.62
    Trama
    0.62
     Mapp
    0.51
    nonatomic
    0.50
     money
    0.50
     MotionEvent
    0.49
     '{@
    0.49
    InteropServices
    0.49
    estroy
    0.46
     Money
    0.46
    Activations Density 0.179%

    No Known Activations