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. 1529
    Prev
    Next
    INDEX
    Explanations

    elements related to character development and casting in storytelling

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

    fictional characters

    np_acts-logits-general · gemini-2.0-flash

    creating or playing characters

    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
    出版年
    -0.87
    adpleegd
    -0.55
    ünste
    -0.53
    şiv
    -0.51
    SBATCH
    -0.51
    دانشنامهٔ
    -0.50
    numerusform
    -0.50
     estekak
    -0.49
    DockStyle
    -0.49
    AddTagHelper
    -0.48
    POSITIVE LOGITS
     characters
    2.11
     character
    1.97
     Characters
    1.78
    character
    1.66
    Characters
    1.65
    characters
    1.64
     Character
    1.64
    Character
    1.61
     CHARACTERS
    1.54
     personaje
    1.51
    Activations Density 0.286%

    No Known Activations