© 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. 6057
    Prev
    Next
    INDEX
    Explanations

    terms related to connectivity within networks or systems

    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
     doInBackground
    -0.52
    ẖ
    -0.48
    __':
    
    -0.43
    \{\\
    -0.42
     pop
    -0.39
     pitch
    -0.38
    HostException
    -0.38
     onPostExecute
    -0.38
     Soit
    -0.37
    JSONException
    -0.37
    POSITIVE LOGITS
     connected
    2.27
     linked
    2.02
    connected
    1.95
     Connected
    1.90
    Connected
    1.81
    linked
    1.66
     associated
    1.66
     attached
    1.65
     affiliated
    1.58
     verbonden
    1.52
    Activations Density 0.207%

    No Known Activations