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. 14-GEMMASCOPE-RES-16K
    6. 8332
    Prev
    Next
    INDEX
    Explanations

    significant events or notable mentions related to various subjects or cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.75
    ſelves
    -0.74
     Reſ
    -0.68
     ſtate
    -0.66
     itſelf
    -0.63
    TypedDataSet
    -0.63
     myſelf
    -0.62
     houſe
    -0.60
     ſtre
    -0.60
     poffible
    -0.60
    POSITIVE LOGITS
     none
    0.43
     voran
    0.37
    hoeddwyd
    0.37
    AndEndTag
    0.37
    findpost
    0.36
     p
    0.34
    のが
    0.34
     sent
    0.33
    のは
    0.33
    CppMethod
    0.33
    Activations Density 0.429%

    No Known Activations