© 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. 8021
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or absence of obligation or significance in actions

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

    the phrase "has something to do with" or similar expressions indicating a causal or relational connection between concepts.

    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
    曖昧さ回避
    -0.49
    istoitu
    -0.48
     AssemblyTitle
    -0.44
     nonatomic
    -0.42
     تعدى
    -0.40
    tinyos
    -0.39
     parachoque
    -0.36
     Tools
    -0.36
    enderror
    -0.36
    ”]
    -0.36
    POSITIVE LOGITS
     do
    0.97
     betrekking
    0.68
    do
    0.59
     pertain
    0.54
     berhubungan
    0.53
     relate
    0.53
     يتيمه
    0.50
     related
    0.50
     relating
    0.50
     riguard
    0.49
    Activations Density 0.119%

    No Known Activations