© 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. 15-GEMMASCOPE-RES-16K
    6. 2963
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document

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

    the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.47
     MainAxisSize
    -1.38
     كومونز
    -1.19
     שוליים
    -1.17
    GEBURTSDATUM
    -1.12
    enumii
    -1.10
    AndEndTag
    -1.10
     nakalista
    -1.07
    
    -1.05
    StoryboardSegue
    -1.04
    POSITIVE LOGITS
    .
    0.54
     a
    0.54
     
    0.52
     "
    0.46
     U
    0.45
     to
    0.45
     the
    0.45
     “
    0.45
    歴
    0.45
     '
    0.44
    Activations Density 0.016%

    No Known Activations