© 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. 0-GEMMASCOPE-RES-16K
    6. 3102
    Prev
    Next
    INDEX
    Explanations

    instances of the word "calculation" and its variations in a mathematical or computational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dieſer
    -0.68
     ſeinen
    -0.67
    #+#
    -0.66
    VYMaps
    -0.66
     müſſen
    -0.64
     étoit
    -0.63
     ſeine
    -0.63
     صوتيه
    -0.63
    <unused43>
    -0.63
     myſelf
    -0.63
    POSITIVE LOGITS
     calculation
    0.93
     computing
    0.84
     Calculation
    0.82
    Calculation
    0.77
     calculations
    0.75
     calculating
    0.75
     calculate
    0.69
    性
    0.68
     calculated
    0.68
     compute
    0.66
    Activations Density 0.385%

    No Known Activations