© 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. 342
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate a process of change or transformation

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

    words or concepts related to negative or disruptive effects and consequences.

    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
    AsUp
    -0.67
     Geſ
    -0.63
     censiti
    -0.58
    Portály
    -0.56
     INTERESAR
    -0.50
     createTime
    -0.50
    ioutil
    -0.50
     produisons
    -0.49
     auffi
    -0.49
     ſein
    -0.49
    POSITIVE LOGITS
    ly
    0.52
     factor
    0.38
     effect
    0.36
     factors
    0.36
     odkazy
    0.35
    astify
    0.35
     estekak
    0.34
    ing
    0.34
     tendances
    0.32
    menden
    0.32
    Activations Density 0.381%

    No Known Activations