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. 1-GEMMASCOPE-RES-16K
    6. 9647
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "http"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -1.01
     HasFactory
    -0.92
    ]")]
    -0.82
     🥰
    -0.79
    msgSender
    -0.77
     covid
    -0.77
    IntoConstraints
    -0.76
     disambiguazione
    -0.74
     insuffisamment
    -0.73
    tvguidetime
    -0.73
    POSITIVE LOGITS
    http
    3.18
     http
    2.41
    Http
    1.22
    ttp
    1.21
     Http
    1.18
     HTTP
    1.09
    HTTP
    1.08
    www
    1.06
    https
    0.82
     www
    0.75
    Activations Density 0.087%

    No Known Activations