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. 1070
    Prev
    Next
    INDEX
    Explanations

    references to specific conditions or settings in context

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

    something is removed or absent

    np_acts-logits-general · gemini-2.0-flash

    eliminated or removed

    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
    \{\\
    -0.55
    ządz
    -0.55
    owna
    -0.53
    chae
    -0.52
    ValueStyle
    -0.49
    JspWriter
    -0.49
    LookAnd
    -0.47
     ".";
    -0.46
    RegressionTest
    -0.46
    Schutz
    -0.46
    POSITIVE LOGITS
     eliminated
    1.69
     removed
    1.65
     deleted
    1.53
     abolished
    1.52
     elimination
    1.50
     delete
    1.48
     disappeared
    1.48
    elimin
    1.46
     removal
    1.46
     elimin
    1.44
    Activations Density 0.851%

    No Known Activations