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. 18-GEMMASCOPE-RES-16K
    6. 8297
    Prev
    Next
    INDEX
    Explanations

    legal terminologies and references to statutes or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences that define or specify something

    np_acts-logits-general · gemini-2.0-flash

    states rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.65
    EndInit
    -0.58
    örté
    -0.53
     Ressource
    -0.52
    Datuak
    -0.51
     distraction
    -0.50
     afectadas
    -0.49
     sosp
    -0.49
     busiest
    -0.49
     Unpublished
    -0.49
    POSITIVE LOGITS
     provisions
    1.16
     provision
    1.16
     specifies
    1.02
    provision
    0.96
     stipul
    0.95
     Provisions
    0.93
     PROVISIONS
    0.85
     specify
    0.84
     prescribes
    0.84
     Provision
    0.82
    Activations Density 0.605%

    No Known Activations