© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 97135
    Prev
    Next
    INDEX
    Explanations

    the concept of storage or safe keeping, particularly in a digital or secure context

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

    vaulted tokens, assault, crypt, implants, office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idée
    -0.39
     Bitter
    -0.37
     Sira
    -0.36
    httphttps
    -0.36
    getText
    -0.35
    MJ
    -0.35
    iS
    -0.35
     problème
    -0.35
    ities
    -0.35
    getAction
    -0.34
    POSITIVE LOGITS
     vault
    2.34
     Vault
    2.34
    Vault
    2.14
    vault
    2.03
     vaults
    1.84
     vaulted
    1.18
     Va
    0.82
    Va
    0.77
    pulseira
    0.70
     Vaughn
    0.68
    Activations Density 0.001%

    No Known Activations