Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1565
    Prev
    Next
    INDEX
    Explanations

    phrases related to making a significant impact or difference

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

    Following the word "make" or "makes"

    np_acts-logits-general · gemini-2.0-flash

    make followed by words

    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
    ilangkan
    -0.53
     intptr
    -0.52
     étoit
    -0.49
     cortas
    -0.49
     auroit
    -0.48
     Ruhm
    -0.48
     quedando
    -0.48
     túl
    -0.48
     Ciro
    -0.48
     Majefty
    -0.47
    POSITIVE LOGITS
    Makes
    0.78
     Makes
    0.73
     MAKE
    0.72
    make
    0.69
     make
    0.68
    LookAnd
    0.66
    abetes
    0.65
     Make
    0.65
     transfieras
    0.64
    matchCondition
    0.64
    Activations Density 0.087%

    No Known Activations