© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8461
    Prev
    Next
    INDEX
    Explanations

    terms related to symbols and their representations, particularly in a programming or mathematical context

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

    "sym" or "symbol" and variants

    np_acts-logits-general · gemini-2.0-flash

    symbol and symmetric variations

    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
     behaupten
    -0.40
     benötigen
    -0.38
    yordu
    -0.38
     fallecido
    -0.37
     enfans
    -0.37
     wystarczy
    -0.36
     asiático
    -0.36
     casó
    -0.36
     vôtre
    -0.36
     llegado
    -0.35
    POSITIVE LOGITS
     Sym
    0.80
     sym
    0.71
    Sym
    0.70
     Symp
    0.68
     SYM
    0.66
    Symp
    0.65
    principalColumn
    0.64
     SYMP
    0.63
     Symb
    0.63
     symp
    0.62
    Activations Density 0.119%

    No Known Activations