© 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. 2-GEMMASCOPE-RES-16K
    6. 13312
    Prev
    Next
    INDEX
    Explanations

    the word 'who' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.56
     Normdatei
    -0.54
    蚪
    -0.50
     surla
    -0.48
     thereto
    -0.46
     theſe
    -0.44
    Dope
    -0.42
     gitu
    -0.42
    URLException
    -0.42
     Meksiku
    -0.42
    POSITIVE LOGITS
    iconque
    0.72
    genen
    0.43
     OTHERS
    0.41
     хто
    0.39
    tableFuture
    0.38
     kepentingan
    0.38
     kẻ
    0.37
     parseFrom
    0.36
     individuals
    0.36
    Demografía
    0.36
    Activations Density 0.182%

    No Known Activations