© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7133
    Prev
    Next
    INDEX
    Explanations

    occurrences of the string data type and related operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.93
    ]--;
    -0.92
    verifyException
    -0.90
     Audiodateien
    -0.89
    expandindo
    -0.89
     FAP
    -0.88
     Koop
    -0.85
     Bick
    -0.85
    Geplaatst
    -0.84
     ſeveral
    -0.84
    POSITIVE LOGITS
     str
    1.59
    str
    1.48
     Str
    1.37
     STR
    1.31
    STR
    1.17
    Str
    1.13
     Stroud
    1.09
    istr
    1.03
    struts
    1.02
     strs
    1.00
    Activations Density 0.050%

    No Known Activations