© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 3147
    Prev
    Next
    INDEX
    Explanations

    terms related to frequency and consistency in actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(/*!
    -0.74
    GenerationType
    -0.64
    IBOutlet
    -0.62
    WriteLiteral
    -0.61
    EndInit
    -0.60
    AnchorStyles
    -0.59
     Familienname
    -0.58
     لينك
    -0.57
    jsonwebtoken
    -0.56
    peteer
    -0.55
    POSITIVE LOGITS
     constantly
    1.21
     continuously
    1.21
     continually
    1.14
     continuous
    1.04
    Continuous
    1.04
     Continuous
    1.04
     constant
    1.02
    不断的
    0.99
     continual
    0.99
     unceasing
    0.94
    Activations Density 0.153%

    No Known Activations