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

    Neuronpedia

    Jacobian LensNEW
    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. 12993
    Prev
    Next
    INDEX
    Explanations

    discussions about the influence and consideration of various factors in different contexts

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

    Followed by "factors"

    np_acts-logits-general · gemini-2.0-flash

    a number of factors

    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
     Reverso
    -0.76
    TagMode
    -0.73
    StoryboardSegue
    -0.66
     Савезне
    -0.65
    WriteBarrier
    -0.62
    出版年
    -0.60
     Abstr
    -0.58
    SOUNDBITE
    -0.57
    stdio
    -0.57
     nightmares
    -0.57
    POSITIVE LOGITS
     factors
    2.68
     Factors
    2.26
    factors
    2.23
     factor
    2.17
    Factors
    2.12
     factores
    2.01
     FACTORS
    1.96
     facteurs
    1.84
     Faktoren
    1.82
    factor
    1.79
    Activations Density 0.583%

    No Known Activations