© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3911
    Prev
    Next
    INDEX
    Explanations

    connections to events or actions that yield significant consequences or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    temporal transitions and causal relationships between events.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.51
    rungsseite
    -0.47
    AsUp
    -0.47
    Jeografia
    -0.44
     '\\;'
    -0.42
    DJANGO
    -0.41
    bisoft
    -0.40
    AutoScaleMode
    -0.39
    蚪
    -0.39
     BytesLike
    -0.38
    POSITIVE LOGITS
    今回の
    0.69
     Tuesday
    0.55
    AndEndTag
    0.54
    這次
    0.54
    此次
    0.52
    这次
    0.51
     Wednesday
    0.50
    Tuesday
    0.49
     Monday
    0.48
     Thursday
    0.48
    Activations Density 0.717%

    No Known Activations