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. 24-GEMMASCOPE-RES-16K
    6. 12702
    Prev
    Next
    INDEX
    Explanations

    details about sorting and organizing information in lists or databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    code or config files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.66
     ostavi
    -0.58
     Logement
    -0.57
     EconPapers
    -0.56
     $\&$
    -0.54
    raborty
    -0.53
     Spisak
    -0.53
    xase
    -0.51
    createStatement
    -0.50
    WriteBarrier
    -0.50
    POSITIVE LOGITS
    _
    2.96
    \_
    1.68
     _
    1.22
    _-_
    1.07
    _*
    1.03
    _{-}
    1.03
    __
    0.99
    _-
    0.97
    _%
    0.97
    _$
    0.97
    Activations Density 1.320%

    No Known Activations