© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3912
    Prev
    Next
    INDEX
    Explanations

    references to phone-related terms and concepts

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

    "phone" or "telephone"

    np_acts-logits-general · gemini-2.0-flash

    phone and telephone contexts

    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
    dad
    -0.67
     father
    -0.61
    zitter
    -0.58
    SourceChecksum
    -0.58
    mothers
    -0.54
    存于互联网档案馆
    -0.54
     Father
    -0.53
     husband
    -0.52
    AxisAlignment
    -0.52
    fathers
    -0.51
    POSITIVE LOGITS
     PHONE
    0.92
     phones
    0.92
     Phone
    0.89
     phone
    0.84
     telephones
    0.82
     Phones
    0.82
     Telephone
    0.79
     telephone
    0.79
     telef
    0.78
    PHONE
    0.78
    Activations Density 0.082%

    No Known Activations