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. 4-GEMMASCOPE-RES-16K
    6. 3399
    Prev
    Next
    INDEX
    Explanations

    terms related to societal norms around parenting and reproductive choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     跳转至
    -0.77
    <bos>
    -0.62
    findpost
    -0.60
     Meksiku
    -0.56
    Παραπομπές
    -0.54
    ,
    -0.54
     poveznice
    -0.54
     ͡°)
    -0.54
    nissen
    -0.54
    सन्दर्भ
    -0.54
    POSITIVE LOGITS
    ISupport
    0.85
    Datuak
    0.74
    rungsseite
    0.71
    AnchorTagHelper
    0.68
    PreferredItem
    0.65
     GenerationType
    0.57
     disambiguazione
    0.56
    BITDA
    0.55
    HostException
    0.55
    ContentAsync
    0.55
    Activations Density 8.724%

    No Known Activations