© 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. 20-GEMMASCOPE-RES-16K
    11. 16245
    Prev
    Next
    INDEX
    Explanations

    conditional statements and functions related to programming and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Euro
    -0.39
    ární
    -0.38
    styleType
    -0.38
    Perc
    -0.37
     Regret
    -0.36
     Porte
    -0.36
    pantalones
    -0.36
    Regret
    -0.36
    viron
    -0.36
     regret
    -0.35
    POSITIVE LOGITS
    ⓧ
    0.52
    PullParser
    0.49
     autorytatywna
    0.49
    IsMutable
    0.49
    ValueGeneration
    0.48
    ScopeManager
    0.47
    Datuak
    0.46
     даже
    0.46
    WriteTagHelper
    0.45
    ंदीखरीदारी
    0.44
    Activations Density 0.479%

    No Known Activations