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. 33-GEMMASCOPE-RES-16K
    6. 7953
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs, specifically those involving table view operations and class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trace
    -0.40
    trace
    -0.39
     TRACE
    -0.36
    ']->
    -0.33
     Trace
    -0.33
     diagnose
    -0.33
     DEBUG
    -0.32
    DEBUG
    -0.32
     négo
    -0.31
     CreateTagHelper
    -0.31
    POSITIVE LOGITS
    !.
    1.01
    !,
    0.94
    !
    0.90
    !..
    0.88
    !?
    0.86
    !...
    0.84
    !;
    0.84
    !:
    0.81
    !”.
    0.81
    !’
    0.80
    Activations Density 0.390%

    No Known Activations