© 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. 24-GEMMASCOPE-RES-16K
    11. 12548
    Prev
    Next
    INDEX
    Explanations

    technical terms and expressions related to software, particularly in programming and licensing contexts

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

    Numbers with decimals

    np_acts-logits-general · gemini-2.0-flash

    autorest with error

    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
    </em>
    -0.34
     -
    -0.32
     snippetHide
    -0.32
    ↵
    -0.30
    ;#
    -0.30
     –
    -0.29
     —
    -0.29
     --
    -0.27
     :
    -0.27
     
    -0.25
    POSITIVE LOGITS
    :✨
    1.13
     myſelf
    1.09
     Monfieur
    1.09
     itſelf
    1.08
     becauſe
    1.08
     raiſ
    1.07
    RegistryLite
    1.06
     Theſe
    1.05
     whoſe
    1.05
     poffe
    1.04
    Activations Density 0.063%

    No Known Activations