© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4459
    Prev
    Next
    INDEX
    Explanations

    instances where different elements or categories are combined or merged

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

    about combining or merging

    np_acts-logits-general · gemini-2.0-flash

    combining elements or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.67
    \{\\
    -0.59
    tvguidetime
    -0.54
    mappedBy
    -0.53
    vistar
    -0.51
     nakalista
    -0.50
    (!__
    -0.50
     noDo
    -0.49
     defaultstate
    -0.49
    Rüyada
    -0.48
    POSITIVE LOGITS
     elements
    0.94
    elements
    0.72
     elementos
    0.65
     technology
    0.63
     expertise
    0.63
     elementy
    0.61
     elementi
    0.58
     Elemente
    0.58
     techniques
    0.57
    Elements
    0.57
    Activations Density 0.356%

    No Known Activations