© 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. 21-GEMMASCOPE-RES-16K
    11. 10800
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases indicating thought processes and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Woodward
    -0.53
    存于互联网档案馆
    -0.49
    cdi
    -0.44
    XtraBars
    -0.44
     Unexpected
    -0.43
    addPreferredGap
    -0.42
     poisson
    -0.41
    
    -0.41
    TemporalType
    -0.41
    即可
    -0.40
    POSITIVE LOGITS
     that
    0.66
    ResumeLayout
    0.60
     Roskov
    0.59
     they
    0.56
     disambiguazione
    0.56
     daß
    0.54
    that
    0.52
     rằng
    0.50
     bahawa
    0.50
     bahwa
    0.50
    Activations Density 0.522%

    No Known Activations