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. 23-GEMMASCOPE-RES-16K
    6. 11906
    Prev
    Next
    INDEX
    Explanations

    terms related to physical properties and characteristics of materials in scientific contexts

    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
     betweenstory
    -1.27
     beginnetje
    -0.95
     للمعارف
    -0.94
     CreateTagHelper
    -0.90
     nahilalakip
    -0.85
    ConstraintMaker
    -0.84
    +#+#
    -0.80
     الحره
    -0.78
    tvguidetime
    -0.77
     متعلقه
    -0.74
    POSITIVE LOGITS
     versus
    0.74
     (=
    0.71
     or
    0.68
     (>
    0.68
     $(
    0.66
     (<
    0.65
    -
    0.62
    まま
    0.62
     vs
    0.61
    -<
    0.60
    Activations Density 2.309%

    No Known Activations