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. 23-GEMMASCOPE-RES-16K
    6. 12544
    Prev
    Next
    INDEX
    Explanations

    phrases indicating organizational or systemic dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     peindre
    -0.48
     gjø
    -0.46
    dAtA
    -0.46
    ьаж
    -0.45
     sjø
    -0.44
     mariée
    -0.43
    UrlResolution
    -0.42
    rolid
    -0.42
     affitto
    -0.41
    TagHelper
    -0.41
    POSITIVE LOGITS
     disappointing
    1.51
     failures
    1.46
     failure
    1.45
     unsatisfactory
    1.44
     failed
    1.43
     failing
    1.40
     inadequate
    1.37
     ineffective
    1.36
     disappointment
    1.35
     disappointed
    1.31
    Activations Density 1.673%

    No Known Activations