© 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. 15706
    Prev
    Next
    INDEX
    Explanations

    terms related to dog harnesses and lead configurations

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

    words and phrases related to ropes, cables, and similar cord-like objects used for pulling or suspending things.

    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
    piring
    -0.44
     Fieber
    -0.42
     disambiguazione
    -0.42
    ikali
    -0.40
     Catawiki
    -0.39
    usitis
    -0.39
     aussch
    -0.38
    rån
    -0.36
    AndEndTag
    -0.35
    SequentialGroup
    -0.35
    POSITIVE LOGITS
     rope
    1.13
     Rope
    0.92
    Rope
    0.92
     ropes
    0.90
     hooks
    0.89
     loops
    0.87
     knots
    0.86
     knot
    0.85
    rope
    0.84
     chains
    0.82
    Activations Density 0.324%

    No Known Activations