© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8138
    Prev
    Next
    INDEX
    Explanations

    occurrences of the programming language PHP

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onsumsi
    -0.42
     engran
    -0.38
    anius
    -0.38
     pungkas
    -0.37
     bilg
    -0.37
     hoogte
    -0.37
    ikations
    -0.35
    stup
    -0.35
     perlindungan
    -0.35
     acuerdos
    -0.35
    POSITIVE LOGITS
    php
    0.78
    PerformLayout
    0.66
     للاسماء
    0.62
    ContentLoaded
    0.61
    DIPSETTING
    0.61
    endphp
    0.60
     createSlice
    0.59
     php
    0.59
    __["
    0.56
    Php
    0.55
    Activations Density 0.104%

    No Known Activations