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-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 4419
    Prev
    Next
    INDEX
    Explanations

    instances of function definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pelear
    -0.66
     shingle
    -0.65
    EndContext
    -0.64
     creeds
    -0.63
     shingles
    -0.63
     McGregor
    -0.59
     Már
    -0.58
     Elin
    -0.58
     MTC
    -0.57
     tendered
    -0.56
    POSITIVE LOGITS
     void
    1.51
    void
    1.50
    Void
    1.31
     VOID
    1.27
    VOID
    1.21
     Void
    1.16
     voids
    1.11
    onedDateTime
    0.94
     Nieto
    0.91
    #+#
    0.88
    Activations Density 0.029%

    No Known Activations