© 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. 3-GEMMASCOPE-RES-16K
    6. 6596
    Prev
    Next
    INDEX
    Explanations

    technical terms related to alignment and structure in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mature
    -0.40
    Bureau
    -0.38
     match
    -0.38
    liseum
    -0.38
     nationwide
    -0.37
    nation
    -0.37
     bureau
    -0.36
    reif
    -0.36
     MEX
    -0.36
    setCell
    -0.36
    POSITIVE LOGITS
     Alignment
    0.71
    Alignment
    0.70
    getLogger
    0.68
     alignment
    0.61
    alignment
    0.60
    DockStyle
    0.58
     làm
    0.56
    DIPSETTING
    0.50
    setVerticalGroup
    0.50
    subset
    0.49
    Activations Density 1.290%

    No Known Activations