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. 24-GEMMASCOPE-RES-16K
    6. 4608
    Prev
    Next
    INDEX
    Explanations

    statements made by authorities or experts regarding events or claims

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

    "said" followed by dialogue

    np_acts-logits-general · gemini-2.0-flash

    attributing speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ourselves
    -0.63
    which
    -0.57
     которых
    -0.54
     moi
    -0.50
    そして
    -0.49
    的我
    -0.49
    yourself
    -0.47
     yetu
    -0.47
     and
    -0.46
    them
    -0.46
    POSITIVE LOGITS
     they
    1.00
     there
    1.00
     although
    0.97
     it
    0.94
     pihaknya
    0.79
    脚注の使い方
    0.79
    expandindo
    0.79
     while
    0.78
     Tuesday
    0.78
     Thursday
    0.76
    Activations Density 0.176%

    No Known Activations