© 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. 10533
    Prev
    Next
    INDEX
    Explanations

    the phrase "along with" or similar phrases indicating accompaniment or addition

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

    the phrase "Along with" that introduces accompanying or additional information.

    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
    PhysRev
    -0.43
    :✨
    -0.42
    ⇑
    -0.41
    moveToFirst
    -0.39
    ophageal
    -0.39
     Bibl
    -0.38
    FL
    -0.38
    Bet
    -0.38
    SpringBootTest
    -0.37
    Alban
    -0.36
    POSITIVE LOGITS
    Along
    0.73
     Along
    0.72
     ALONG
    0.71
    along
    0.68
     along
    0.62
    sides
    0.56
    SIDE
    0.56
     lines
    0.55
    Хьажоргаш
    0.54
    lines
    0.54
    Activations Density 0.062%

    No Known Activations