© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 4506
    Prev
    Next
    INDEX
    Explanations

    conditional statements and comparisons in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     act
    -0.58
    abestanden
    -0.56
    cèse
    -0.51
    ntz
    -0.50
     يتيمه
    -0.49
    quante
    -0.47
     acted
    -0.47
    createClass
    -0.47
     magasiner
    -0.46
    Flour
    -0.46
    POSITIVE LOGITS
    equals
    0.87
    equalsIgnoreCase
    0.80
    content
    0.64
    ReusableCell
    0.63
     equals
    0.63
    matches
    0.59
     WaitForSeconds
    0.58
     Equals
    0.56
    startsWith
    0.55
    bukkit
    0.53
    Activations Density 0.140%

    No Known Activations