© 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. 1-GEMMASCOPE-RES-16K
    11. 3148
    Prev
    Next
    INDEX
    Explanations

    terms related to cognitive functions and cognitive impairments

    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
     HasFactory
    -0.53
     ferons
    -0.39
     صوتيه
    -0.39
    fitriones
    -0.39
     getragen
    -0.38
     détach
    -0.38
    gänge
    -0.37
     expériment
    -0.36
     geschieht
    -0.36
     mystère
    -0.36
    POSITIVE LOGITS
    intuitive
    0.68
     intuitively
    0.67
     intuitive
    0.65
     bounced
    0.63
     flipped
    0.63
     prejudice
    0.62
     navigate
    0.61
     intuiti
    0.60
    flip
    0.60
     bounce
    0.59
    Activations Density 0.439%

    No Known Activations