Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2440
    Prev
    Next
    INDEX
    Explanations

    demographic data relating to income and population statistics

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

    Followed by a period, "and", comma, or "in"

    np_acts-logits-general · gemini-2.0-flash

    families and demographics

    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
    出版年
    -0.54
    İstinadlar
    -0.53
    igshid
    -0.51
    arned
    -0.49
     anzi
    -0.48
     Städten
    -0.48
    DataAnnotations
    -0.48
     OnTriggerEnter
    -0.48
    DebuggerNonUser
    -0.47
    ACTERS
    -0.47
    POSITIVE LOGITS
    cadeira
    0.56
     tartalomajánló
    0.55
     Mexicano
    0.52
     parseFrom
    0.51
    SBATCH
    0.51
    ettbewerb
    0.51
     beweg
    0.49
     meis
    0.48
    ettbewer
    0.48
     AssemblyProduct
    0.48
    Activations Density 0.128%

    No Known Activations