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

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 5982
    Prev
    Next
    INDEX
    Explanations

    instructions for mold removal and moisture management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SupportActionBar
    -0.59
    oredCriteria
    -0.59
    Datuak
    -0.56
    rubin
    -0.55
     Bingham
    -0.53
     Falk
    -0.53
    arschu
    -0.52
     chì
    -0.51
    BRC
    -0.51
    MessageInfo
    -0.49
    POSITIVE LOGITS
     moisture
    1.51
     humidity
    1.46
     Moisture
    1.32
     humid
    1.30
     moist
    1.27
     Humidity
    1.25
    Moisture
    1.21
    moisture
    1.20
     Moist
    1.19
     Humid
    1.18
    Activations Density 0.617%

    No Known Activations