© 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. 14072
    Prev
    Next
    INDEX
    Explanations

    mentions of specific tablet models and their features

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

    product model names and specifications (particularly "Samsung GALAXY Tab 7.0 Plus" and associated technical details).

    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
     Wright
    -0.35
     Sha
    -0.34
    lış
    -0.32
     recha
    -0.32
     Sherwood
    -0.32
     Gordon
    -0.32
     phương
    -0.31
     Sorensen
    -0.31
     au
    -0.31
     Harlow
    -0.31
    POSITIVE LOGITS
     Samsung
    1.02
    Samsung
    0.95
     samsung
    0.93
     SAMSUNG
    0.93
     سامسونگ
    0.86
     Galaxy
    0.84
    Galaxy
    0.80
    三星
    0.75
    samsung
    0.71
     korea
    0.69
    Activations Density 0.135%

    No Known Activations