Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 979
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structural elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    final manuscript

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.67
    ChatColor
    -0.61
    Hochspringen
    -0.60
    NameInMap
    -0.56
     UIApplication
    -0.51
    FXML
    -0.50
    regas
    -0.49
     getItemCount
    -0.47
    DotNetBar
    -0.47
     demurrer
    -0.47
    POSITIVE LOGITS
     المعيارى
    0.69
     NUKAT
    0.65
     חיצוניים
    0.63
     getRule
    0.60
     continúas
    0.57
    帖最后由
    0.57
     reservados
    0.56
     transférez
    0.56
     comuniques
    0.55
     صوتيه
    0.55
    Activations Density 0.099%

    No Known Activations