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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9712
    Prev
    Next
    INDEX
    Explanations

    references to academic programs and faculties within educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ungsver
    -0.47
    MockMvc
    -0.45
    Mog
    -0.43
    toBe
    -0.42
     gada
    -0.41
    ConstraintLayout
    -0.41
    nock
    -0.41
    yeri
    -0.39
     motivasi
    -0.39
    anton
    -0.38
    POSITIVE LOGITS
     arts
    1.44
     sciences
    1.37
     humanities
    1.23
     Arts
    1.23
     Sciences
    1.20
    Arts
    1.19
    arts
    1.17
     science
    1.13
    sciences
    1.10
     Humanities
    1.04
    Activations Density 0.139%

    No Known Activations