© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4146
    Prev
    Next
    INDEX
    Explanations

    patterns of concatenated functions and commands in a programming or scripting context

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

    Lines starting with "+" in code diffs

    np_acts-logits-general · gemini-2.0-flash

    added code lines

    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
     betweenstory
    -0.64
     chi̍t
    -0.57
    -};
    -0.56
     initComponents
    -0.54
    таратура
    -0.54
    gameserver
    -0.54
    -/**
    -0.53
    migrationBuilder
    -0.52
     Athene
    -0.51
    ыгана
    -0.51
    POSITIVE LOGITS
    +:+
    0.61
    StoryboardSegue
    0.59
    +
    0.56
    WriteTagHelper
    0.54
    +)
    0.52
    +.
    0.51
    WritableDatabase
    0.50
    FieldDescriptor
    0.50
    +$
    0.50
    licit
    0.49
    Activations Density 0.079%

    No Known Activations