© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or quantity of various entities or concepts

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

    the phrase "There are" at the beginning of statements introducing multiple options or categories.

    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
    LayoutConstraint
    -0.52
    mybatisplus
    -0.52
    <?
    -0.52
     HasFactory
    -0.52
    InitStruct
    -0.50
    InstrumentedTest
    -0.48
     betweenstory
    -0.47
    posedge
    -0.44
    AutoField
    -0.43
    ActionCreators
    -0.42
    POSITIVE LOGITS
     plenty
    0.70
     certain
    0.68
     some
    0.67
     many
    0.64
     few
    0.63
     several
    0.58
     fewer
    0.56
     various
    0.53
     different
    0.51
     two
    0.50
    Activations Density 0.140%

    No Known Activations