© 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. 21-GEMMASCOPE-RES-16K
    6. 13254
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements and constructs related to conditional statements and logical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.65
    //
    -0.56
    \{\\
    -0.56
     للاسماء
    -0.52
     FontWeight
    -0.52
     שוליים
    -0.49
     HasFactory
    -0.48
    stuffs
    -0.47
    AppCompatTheme
    -0.46
    UserScript
    -0.46
    POSITIVE LOGITS
     propOrder
    0.79
     وتسجيلات
    0.71
    IntoConstraints
    0.71
    ̸
    0.71
    seamnă
    0.70
     disambiguazione
    0.65
     vícti
    0.65
     niyang
    0.64
     préc
    0.64
     pessoais
    0.63
    Activations Density 0.973%

    No Known Activations