© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4148
    Prev
    Next
    INDEX
    Explanations

    various forms of the IP address protocol and related terms

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

    Tokens followed by "PROTO" or related terms

    np_acts-logits-general · gemini-2.0-flash

    IPH, IPP, IPL, IP1

    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
    MigrationBuilder
    -0.67
     autorytatywna
    -0.57
    unhofer
    -0.55
    новниш
    -0.55
    nador
    -0.52
    addCriterion
    -0.52
    Personendaten
    -0.51
    λλη
    -0.51
    oredCriteria
    -0.51
     виправивши
    -0.50
    POSITIVE LOGITS
    otesi
    0.66
    tvguidetime
    0.59
    ynb
    0.57
    sec
    0.56
    arraycopy
    0.53
    UMS
    0.53
    address
    0.53
    higen
    0.53
     محفوظة
    0.52
     kelas
    0.50
    Activations Density 0.202%

    No Known Activations