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. 8627
    Prev
    Next
    INDEX
    Explanations

    specific names and mentions related to academic and scientific contexts

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

    Followed by a punctuation mark or special character

    np_acts-logits-general · gemini-2.0-flash

    uch, atch, it, ouch, duch, psych, ches

    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
    ränkt
    -0.84
     referenties
    -0.83
    djangoproject
    -0.71
     angekommen
    -0.67
    uginosa
    -0.67
     disambiguazione
    -0.66
    amssymb
    -0.66
     Eno
    -0.66
     arrep
    -0.65
     animaux
    -0.65
    POSITIVE LOGITS
    s
    0.84
     Hach
    0.84
     Kach
    0.81
    hhhh
    0.78
     Uch
    0.77
    Lach
    0.76
    hhhhhhhh
    0.73
     trich
    0.71
     Luch
    0.71
    ich
    0.71
    Activations Density 0.263%

    No Known Activations