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. 11-GEMMASCOPE-RES-16K
    6. 7699
    Prev
    Next
    INDEX
    Explanations

    conditional statements involving inequality checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     katal
    -0.69
    7
    -0.65
     tap
    -0.60
    -
    -0.58
    тири
    -0.56
    holz
    -0.55
    TAP
    -0.55
    atud
    -0.55
     TAP
    -0.54
     Tap
    -0.54
    POSITIVE LOGITS
     !=
    1.41
    )!=
    1.21
    ]!=
    1.21
    ()!=
    1.19
    !=
    1.15
     Normdatei
    1.10
    شهاد
    1.07
    endphp
    0.99
     FetchType
    0.96
    tonsoft
    0.96
    Activations Density 0.032%

    No Known Activations