© 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. 22-GEMMASCOPE-RES-16K
    6. 5905
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their significance within the text

    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
     beneficio
    -0.31
     approximation
    -0.29
     votación
    -0.28
     formation
    -0.28
     division
    -0.28
    UNRELATED
    -0.27
     vote
    -0.27
     mean
    -0.27
    OOTDTY
    -0.27
     viz
    -0.26
    POSITIVE LOGITS
    rungsseite
    0.77
    Personendaten
    0.71
    IntoConstraints
    0.67
    ніципалі
    0.66
    httphttps
    0.64
    AutoScaleMode
    0.64
     kasarigan
    0.63
     通販
    0.62
     EconPapers
    0.61
    AndEndTag
    0.61
    Activations Density 0.066%

    No Known Activations