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. 16-GEMMASCOPE-RES-16K
    6. 14726
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate certainty or necessity around actions or states

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

    Follows "'t be" or "may be"

    np_acts-logits-general · gemini-2.0-flash

    may be or contracted verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.87
    =?,
    -0.79
    Portale
    -0.77
     noDo
    -0.75
     насељу
    -0.75
    numerusform
    -0.74
    Tikang
    -0.73
    ########.
    -0.73
    ")"
    -0.73
    WithMany
    -0.73
    POSITIVE LOGITS
     not
    0.47
     saying
    0.46
     mulighed
    0.46
     aceea
    0.45
    .
    0.44
     that
    0.43
    atnya
    0.41
     doute
    0.41
    ,
    0.39
    зумі
    0.39
    Activations Density 1.395%

    No Known Activations