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. 8-GEMMASCOPE-RES-16K
    6. 5866
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and functions

    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
     JAXB
    -0.52
     pathlib
    -0.49
     microbiome
    -0.48
    flashdata
    -0.47
    InSection
    -0.46
     跳转至
    -0.45
    âme
    -0.45
    XMLSchema
    -0.45
     ostensibly
    -0.44
    Viited
    -0.44
    POSITIVE LOGITS
    <bos>
    0.92
     الحره
    0.82
    AddTagHelper
    0.70
    RTGC
    0.67
    олові
    0.66
    ]^{-
    0.64
    SourceChecksum
    0.63
    vician
    0.62
    WriteTagHelper
    0.62
     Roskov
    0.60
    Activations Density 0.311%

    No Known Activations