Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 5728
    Prev
    Next
    INDEX
    Explanations

    statements about existence, reality, and the nature of being

    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
    queryInterface
    -0.57
     defStyleAttr
    -0.55
    люс
    -0.53
    ORUM
    -0.52
     ilg
    -0.51
     típica
    -0.49
    urally
    -0.48
     típico
    -0.48
     restTemplate
    -0.47
     típicos
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.74
    تقاوى
    0.67
     overrated
    0.67
     Administrativna
    0.66
     fickle
    0.58
     everything
    0.58
    WriteBarrier
    0.57
     BoxDecoration
    0.57
     never
    0.57
    /=
    0.57
    Activations Density 0.369%

    No Known Activations