© 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. 7-GEMMASCOPE-RES-16K
    11. 15736
    Prev
    Next
    INDEX
    Explanations

    terms related to retention and holding onto things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.63
    InputBorder
    -0.60
     defaultstate
    -0.59
    astify
    -0.59
    expandindo
    -0.57
    contentLoaded
    -0.56
    NameInMap
    -0.55
    raszamy
    -0.54
    zzleHttp
    -0.53
    ècie
    -0.53
    POSITIVE LOGITS
     retention
    2.47
     retained
    2.41
     retain
    2.41
     retaining
    2.30
     Retention
    2.27
    retention
    2.16
     retains
    2.13
    Retention
    2.08
    retain
    2.08
    Retain
    1.91
    Activations Density 0.114%

    No Known Activations