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. 24-GEMMASCOPE-RES-16K
    6. 13921
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "Am" or its variations, indicating a focus on the first-person perspective or self-reference

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

    "Am" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    Am prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.66
     Layer
    -0.58
     layers
    -0.58
     cherchés
    -0.55
     Meksiku
    -0.54
     насељу
    -0.54
    jooq
    -0.54
    ⏜
    -0.53
    AddTagHelper
    -0.53
     cuad
    -0.53
    POSITIVE LOGITS
    assing
    0.55
    usement
    0.52
     Am
    0.51
    herst
    0.51
    endgroup
    0.50
    ulets
    0.49
     azon
    0.49
    }))
    
    0.49
    dram
    0.49
     Pm
    0.49
    Activations Density 0.102%

    No Known Activations