© 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. 28-GEMMASCOPE-RES-16K
    11. 7783
    Prev
    Next
    INDEX
    Explanations

    instances of the word "many" and variations related to quantities or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "many" occurring in sentences

    np_acts-logits-general · gemini-2.0-flash

    many of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    şört
    -0.52
    
    -0.45
    Composable
    -0.43
     Cognition
    -0.43
    brate
    -0.42
    Sme
    -0.42
    ględ
    -0.42
    sapp
    -0.42
     Crusoe
    -0.41
    Ƚ
    -0.41
    POSITIVE LOGITS
     MANY
    0.78
    MANY
    0.78
     many
    0.67
     Many
    0.67
     tausend
    0.66
    many
    0.63
     times
    0.61
     kinds
    0.60
     different
    0.60
    Many
    0.60
    Activations Density 0.098%

    No Known Activations