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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3090
    Prev
    Next
    INDEX
    Explanations

    genetic sequences and specific scientific references related to molecular biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.57
    riwal
    -0.45
     '\\;'
    -0.44
     pory
    -0.42
    HasAnnotation
    -0.42
    Искәрмәләр
    -0.41
     Meck
    -0.41
    出版年
    -0.41
    perfectly
    -0.41
     محفوظة
    -0.40
    POSITIVE LOGITS
     BoxDecoration
    0.52
     endblock
    0.52
    Referanser
    0.45
     betweenstory
    0.45
     Normdatei
    0.43
    ⤒
    0.40
     [*]
    0.40
     مشين
    0.38
     OMITBAD
    0.38
    mogat
    0.37
    Activations Density 8.696%

    No Known Activations