© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8184
    Prev
    Next
    INDEX
    Explanations

    terms associated with the concept of restoration or returning something to a previous state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ListItemIcon
    -0.46
     ब्रेकडाउन
    -0.43
    istoitu
    -0.39
    retty
    -0.39
    AndEndTag
    -0.36
    huk
    -0.35
     Lumin
    -0.35
     dictation
    -0.34
    nocache
    -0.34
     Recep
    -0.34
    POSITIVE LOGITS
     restored
    2.00
     revived
    1.89
     restoring
    1.88
     regaining
    1.82
     restoration
    1.82
     regained
    1.82
     reinstated
    1.81
     reviving
    1.80
     revival
    1.78
     restore
    1.73
    Activations Density 0.319%

    No Known Activations