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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 607
    Prev
    Next
    INDEX
    Explanations

    concepts and elements related to technology and digital advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     htons
    -0.59
    AutoScaleMode
    -0.58
     terecht
    -0.57
    MockMvc
    -0.55
    Referanser
    -0.54
    ChildScrollView
    -0.53
    TypedDataSet
    -0.52
     BorderRadius
    -0.52
    createQuery
    -0.51
    EDEFAULT
    -0.51
    POSITIVE LOGITS
     allow
    2.98
     allows
    2.88
     allowing
    2.84
    Allow
    2.56
     Allowing
    2.55
     Allow
    2.53
    allow
    2.48
    allowing
    2.44
     Allows
    2.42
     permitting
    2.40
    Activations Density 1.207%

    No Known Activations