© 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. 16-GEMMASCOPE-RES-16K
    11. 8003
    Prev
    Next
    INDEX
    Explanations

    phrases related to credit and acknowledgment in contexts of ownership or contributions

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

    Following "makes," "an," or a hyphen

    np_acts-logits-general · gemini-2.0-flash

    makes it | perimeter | exclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.89
    berdayakan
    -0.74
     pleaſure
    -0.73
     ―――――
    -0.72
    mặt
    -0.70
    ^(@)
    -0.65
    ientôt
    -0.63
    HORE
    -0.62
    odyear
    -0.62
     CURIAM
    -0.61
    POSITIVE LOGITS
    MigrationBuilder
    0.62
     this
    0.59
     Auf
    0.55
     Per
    0.51
     Gar
    0.50
     argint
    0.49
    ˌ
    0.49
    enumii
    0.49
    motic
    0.48
    this
    0.48
    Activations Density 0.811%

    No Known Activations