Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1033
    Prev
    Next
    INDEX
    Explanations

    phrases related to descriptions and specifications in formal documents

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

    "[something] described in [reference]"

    np_acts-logits-general · gemini-2.0-flash

    described in or above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جمعیت
    -0.50
     gabbana
    -0.49
    TargetException
    -0.48
     Jars
    -0.46
    ImageContext
    -0.46
    readFileSync
    -0.45
     Sandler
    -0.45
    DeleteBehavior
    -0.45
     forceps
    -0.45
    lobo
    -0.44
    POSITIVE LOGITS
    sizeCache
    0.46
     represented
    0.46
     shown
    0.44
    represented
    0.44
     listed
    0.43
    shown
    0.42
     exemplified
    0.41
     below
    0.41
     δημο
    0.40
     illustrated
    0.40
    Activations Density 0.507%

    No Known Activations