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. 39-GEMMASCOPE-RES-16K
    6. 4368
    Prev
    Next
    INDEX
    Explanations

    variables and data structures used in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ousands
    -0.48
     TestCase
    -0.47
     للمعارف
    -0.46
     مرئيه
    -0.45
    batore
    -0.44
     Efq
    -0.44
    TagMode
    -0.43
     strdup
    -0.43
    الإنجليزية
    -0.43
     ComVisible
    -0.43
    POSITIVE LOGITS
     itself
    0.53
     =
    0.44
    ConverterFactory
    0.40
    ########.
    0.39
     benefits
    0.37
     darte
    0.36
     belonged
    0.36
     herself
    0.36
     copied
    0.36
     همچنین
    0.35
    Activations Density 0.281%

    No Known Activations