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. 618
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals or works in popular culture

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

    following "the" that describe something

    np_acts-logits-general · gemini-2.0-flash

    the followed by adjectives

    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
    SharedDtor
    -0.81
     BoxDecoration
    -0.73
    "}>
    -0.65
    saraba
    -0.65
    ()}>
    -0.61
     snippetHide
    -0.61
     doInBackground
    -0.60
     оригіналу
    -0.60
     onOptions
    -0.59
    ngOnInit
    -0.58
    POSITIVE LOGITS
     equally
    0.92
     aptly
    0.91
     infamous
    0.88
     highly
    0.84
     famously
    0.83
     aforementioned
    0.82
     recently
    0.82
     famous
    0.80
     wonderfully
    0.80
     notorious
    0.79
    Activations Density 0.278%

    No Known Activations