© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 14841
    Prev
    Next
    INDEX
    Explanations

    identifiers related to academic publications, such as ISSN, ISBN, and PMID

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

    Identifiers: ISSN, ISBN, PMID

    np_acts-logits-general · gemini-2.0-flash

    standardized identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bege
    -0.54
    utt
    -0.47
    Initializable
    -0.47
     thế
    -0.47
    CYCLE
    -0.46
    menter
    -0.45
     Zay
    -0.45
    ToOne
    -0.45
     kunna
    -0.45
    hasMoreElements
    -0.44
    POSITIVE LOGITS
     ISBN
    1.13
    ISBN
    0.93
     ISSN
    0.84
     ISNI
    0.77
    Autoritní
    0.72
    ISSN
    0.72
     NgModule
    0.71
     SUDOC
    0.71
     BIBSYS
    0.68
    enderror
    0.68
    Activations Density 0.025%

    No Known Activations