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-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15002
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word "many" 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 @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Crusoe
    -0.42
    brate
    -0.41
    Crist
    -0.41
     frontières
    -0.40
    adaptiveStyles
    -0.40
     zubere
    -0.40
    spro
    -0.40
    skap
    -0.40
     Orbital
    -0.40
     droid
    -0.39
    POSITIVE LOGITS
     many
    1.18
     MANY
    1.08
    MANY
    1.02
     Many
    1.00
    many
    0.95
    Many
    0.93
     few
    0.82
    ToMany
    0.81
     muchos
    0.79
    Banyak
    0.79
    Activations Density 0.080%

    No Known Activations