© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12632
    Prev
    Next
    INDEX
    Explanations

    references to identifiers or IDs in a code context

    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
    rungsseite
    -0.80
     jsPsych
    -0.59
    URLException
    -0.56
     GenerationType
    -0.54
     identification
    -0.52
    SBATCH
    -0.52
     identificación
    -0.48
     getID
    -0.47
    JSONException
    -0.47
     jLabel
    -0.46
    POSITIVE LOGITS
    Id
    1.38
    Im
    0.76
     Id
    0.68
    Ip
    0.65
     Im
    0.59
    Il
    0.59
    Ik
    0.54
    In
    0.51
    évaluateur
    0.47
    Is
    0.47
    Activations Density 0.201%

    No Known Activations