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. 6420
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to academic and professional qualifications

    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
    :✨
    -0.66
    rungsseite
    -0.63
    EndGlobalSection
    -0.60
    ंदीखरीदारी
    -0.57
     createSlice
    -0.55
     indisponible
    -0.53
    WireFormatLite
    -0.53
     ligiloj
    -0.53
     firebaseConfig
    -0.53
    complexContent
    -0.52
    POSITIVE LOGITS
    ors
    1.54
    ORS
    1.38
    OR
    1.21
    ori
    1.16
    oring
    1.16
    ored
    1.14
    ora
    1.12
    ორ
    1.07
    ory
    1.05
    oris
    1.05
    Activations Density 0.448%

    No Known Activations