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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14604
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational strategies and management within healthcare contexts

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

    Numbers followed by a unit or other abbreviation

    np_acts-logits-general · gemini-2.0-flash

    names followed by qualifiers

    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
    存于互联网档案馆
    -0.82
    .
    -0.72
    ."""
    -0.69
    。
    -0.69
    .[/
    -0.67
    .},
    -0.65
    .",
    -0.61
     kuiten
    -0.60
     withal
    -0.59
    ).]
    -0.59
    POSITIVE LOGITS
    ²/
    0.61
    StoryboardSegue
    0.60
    Rohy
    0.59
    "]="
    0.59
    WithIOException
    0.58
     ""
    
    0.58
     \&
    0.57
    ὸν
    0.56
    ENDE
    0.56
    ]--;
    0.56
    Activations Density 0.853%

    No Known Activations