© 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. 18-GEMMASCOPE-RES-16K
    11. 3925
    Prev
    Next
    INDEX
    Explanations

    questions and queries related to instructions or guidance

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

    Following an interrogative "how"

    np_acts-logits-general · gemini-2.0-flash

    how to do something

    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
    posedge
    -0.91
    OGND
    -0.90
    StoryboardSegue
    -0.89
    waitKey
    -0.78
    EndGlobalSection
    -0.74
    "])
    -0.73
    featureID
    -0.72
    -};
    -0.71
     INTERESAR
    -0.71
    GraphicsUnit
    -0.71
    POSITIVE LOGITS
     do
    0.64
    do
    0.55
     simply
    0.52
     get
    0.49
     yapılır
    0.48
     باید
    0.48
    közi
    0.48
     πρέπει
    0.47
    ต้อง
    0.47
     goes
    0.47
    Activations Density 0.251%

    No Known Activations