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. 8761
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to rights and regulations

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

    negation or disagreement

    np_acts-logits-general · gemini-2.0-flash

    unnecessary rejection or change

    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
     probably
    -0.58
    probably
    -0.58
    somewhat
    -0.57
     somewhat
    -0.56
    albeit
    -0.55
     presumably
    -0.54
     Probably
    -0.53
     einiges
    -0.53
     albeit
    -0.52
     gynnwys
    -0.52
    POSITIVE LOGITS
     unnecessarily
    1.06
     needlessly
    1.00
     anymore
    0.95
     blindly
    0.86
     EconPapers
    0.85
     unduly
    0.80
    oredCriteria
    0.76
     inneces
    0.76
    necessarily
    0.73
     unnecessary
    0.71
    Activations Density 0.409%

    No Known Activations