© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 16034
    Prev
    Next
    INDEX
    Explanations

    relations and connections within family structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="@+
    -0.55
     guest
    -0.52
     Guest
    -0.50
    Kjelder
    -0.50
    izontal
    -0.49
     nakalista
    -0.48
    icit
    -0.48
    streifen
    -0.48
    iyor
    -0.47
    Guest
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.90
    tagHelperRunner
    0.67
     pinulongan
    0.67
    principalTable
    0.66
    fjspx
    0.65
     JpaRepository
    0.65
     صوتيه
    0.64
    oredCriteria
    0.62
    InjectAttribute
    0.61
    lgari
    0.60
    Activations Density 0.054%

    No Known Activations