© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5501
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting marks that indicate structure or emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ControllerAdvice
    -0.52
    Rptr
    -0.52
    جمعیت
    -0.50
    Citiți
    -0.50
     numerus
    -0.48
    стта
    -0.46
     тут
    -0.46
    icznego
    -0.45
    sense
    -0.45
    ibi
    -0.44
    POSITIVE LOGITS
     something
    0.97
     according
    0.83
     although
    0.81
    something
    0.80
     prompting
    0.78
     marking
    0.70
     joining
    0.69
     effectively
    0.68
     though
    0.68
     sparking
    0.67
    Activations Density 0.284%

    No Known Activations