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. 25-GEMMASCOPE-RES-16K
    6. 4695
    Prev
    Next
    INDEX
    Explanations

    phrases related to goals and aims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.65
     aren
    -0.63
    ValueStyle
    -0.62
     aient
    -0.60
    >>()
    -0.59
    IUrlHelper
    -0.59
     représentent
    -0.57
     existem
    -0.57
     Administrativna
    -0.57
     arent
    -0.57
    POSITIVE LOGITS
     was
    2.75
     была
    1.12
     был
    1.12
    was
    1.10
     était
    1.07
    Was
    0.96
     була
    0.95
     був
    0.94
     было
    0.93
     Was
    0.93
    Activations Density 1.030%

    No Known Activations