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. 4614
    Prev
    Next
    INDEX
    Explanations

    references to foundations and community support programs

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

    Followed by "also" or similar words

    np_acts-logits-general · gemini-2.0-flash

    also

    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
    minecraft
    -0.60
    intura
    -0.58
    ostro
    -0.56
    apimachinery
    -0.56
     colspan
    -0.56
    openConnection
    -0.55
    iega
    -0.54
    attles
    -0.54
    chapper
    -0.53
    endere
    -0.52
    POSITIVE LOGITS
     also
    3.75
    also
    3.01
    Also
    2.80
     Also
    2.75
     также
    2.59
     también
    2.53
     também
    2.53
     juga
    2.40
     همچنین
    2.38
     également
    2.35
    Activations Density 1.504%

    No Known Activations