© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9341
    Prev
    Next
    INDEX
    Explanations

    references to childhood experiences and family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wireType
    -0.34
    Datuak
    -0.32
     tamaños
    -0.32
     TRABAJO
    -0.32
     Zwie
    -0.31
     löytyy
    -0.31
    quiera
    -0.31
    setVerticalGroup
    -0.30
    Demografía
    -0.30
     zdrav
    -0.30
    POSITIVE LOGITS
     childhood
    0.82
    Childhood
    0.69
     Childhood
    0.68
    ScopeManager
    0.68
     Kindheit
    0.61
    PreferredItem
    0.60
     AttributeSet
    0.59
     tartalomajánló
    0.58
     boyhood
    0.58
    SequentialGroup
    0.57
    Activations Density 0.366%

    No Known Activations