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. 3208
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and structures

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

    XML tags

    np_acts-logits-general · gemini-2.0-flash

    degrees celsius

    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
     type
    -0.47
     K
    -0.47
     or
    -0.47
     p
    -0.44
    K
    -0.43
    execSQL
    -0.42
    ,
    -0.41
     diámetro
    -0.40
    hu
    -0.40
     not
    -0.40
    POSITIVE LOGITS
     XNUMX
    1.05
     ་་
    1.02
    ^(@)
    1.02
     ſind
    0.99
    OGND
    0.97
    ,:);
    0.94
     iſt
    0.93
    ՚
    0.93
    ')));
    0.92
    __":
    
    0.90
    Activations Density 0.111%

    No Known Activations