© 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. 15-GEMMASCOPE-RES-16K
    11. 12642
    Prev
    Next
    INDEX
    Explanations

    specific formats and structures related to birthdates and personal information about notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.46
    actéris
    -0.40
    cont
    -0.37
     Drittan
    -0.36
     Crow
    -0.35
     drit
    -0.35
    équ
    -0.35
    jal
    -0.35
    kmäler
    -0.34
    мая
    -0.34
    POSITIVE LOGITS
    __*/
    1.13
    ंदीखरीदारी
    1.10
    ⓧ
    1.04
    InjectAttribute
    1.02
     >=",
    0.97
    Personensuche
    0.95
     ExecuteAsync
    0.95
    BeginContext
    0.92
    httphttps
    0.91
    ThroughAttribute
    0.91
    Activations Density 0.121%

    No Known Activations