© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9049
    Prev
    Next
    INDEX
    Explanations

    relationships and family dynamics among people, especially focusing on stepfamily structures and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.57
    SequentialGroup
    -0.56
    AndEndTag
    -0.55
     kasarigan
    -0.54
    RenderAtEndOf
    -0.52
    arangay
    -0.51
    ſelves
    -0.50
    PostInfinity
    -0.50
    HostException
    -0.49
    MarshalTo
    -0.49
    POSITIVE LOGITS
     adopted
    0.38
     pintu
    0.31
     resort
    0.30
    enumerable
    0.30
     ^=
    0.30
    adopted
    0.29
     adopt
    0.29
     caretaker
    0.28
     Kuns
    0.28
    --}}
    0.28
    Activations Density 0.132%

    No Known Activations