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. 14491
    Prev
    Next
    INDEX
    Explanations

    figures or graphs referenced in the text

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

    Figure references, often with a letter

    np_acts-logits-general · gemini-2.0-flash

    figures and citations

    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
     nahilalakip
    -0.93
    IUrlHelper
    -0.68
     Vikipedi
    -0.63
     iconFacebook
    -0.58
    AnchorStyles
    -0.57
    merksam
    -0.57
    tagHelperRunner
    -0.57
    الدراسه
    -0.54
    AddRange
    -0.54
    tagHelper
    -0.53
    POSITIVE LOGITS
     doPost
    0.51
    ISupport
    0.51
    dexter
    0.51
    SPATH
    0.47
     prefeitura
    0.46
    EFAULT
    0.45
    ENOMEM
    0.44
     berço
    0.44
    IConfiguration
    0.44
    SizeF
    0.43
    Activations Density 0.656%

    No Known Activations