© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 7688
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific methods and procedures

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

    following commas

    np_acts-logits-general · gemini-2.0-flash

    usually, typically, or preferably

    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
     MwSt
    -0.49
    Parcelable
    -0.45
    нодоро
    -0.44
     outre
    -0.44
     NSCoder
    -0.43
    csolódó
    -0.42
    voja
    -0.41
    NotNil
    -0.40
    HttpGet
    -0.40
    ZZO
    -0.40
    POSITIVE LOGITS
     preferably
    1.50
     usually
    1.35
     typically
    1.29
    usually
    1.27
    preferably
    1.23
    typically
    1.21
     Typically
    1.15
    Typically
    1.15
     Preferably
    1.15
     Usually
    1.14
    Activations Density 0.570%

    No Known Activations