© 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. 8063
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks, particularly those indicating relationships, conditions, or contrasts

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

    comparative statements where one thing is contrasted with another using "than."

    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
    +#+#
    -0.82
     betweenstory
    -0.75
    featureID
    -0.74
     Beſ
    -0.67
    #+#
    -0.66
     Theſe
    -0.66
     Efq
    -0.66
     Monfieur
    -0.65
    httphttps
    -0.65
     myſelf
    -0.65
    POSITIVE LOGITS
     the
    0.55
     resten
    0.52
     rest
    0.47
     остальные
    0.43
    Rest
    0.36
     remaining
    0.33
     zvyš
    0.31
     remainder
    0.30
    the
    0.30
     Rest
    0.30
    Activations Density 0.491%

    No Known Activations