© 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. 8274
    Prev
    Next
    INDEX
    Explanations

    identifying names and names associated with actions or identities

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

    Preceding or following a person's name

    np_acts-logits-general · gemini-2.0-flash

    introduces person's name

    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
    holo
    -0.40
    ány
    -0.40
    чер
    -0.38
     Emits
    -0.38
    retario
    -0.35
    kosh
    -0.34
    FilterChain
    -0.32
    gnore
    -0.32
    ja
    -0.32
    läge
    -0.31
    POSITIVE LOGITS
     name
    2.94
     Name
    2.51
     names
    2.37
    name
    2.37
     NAME
    2.34
    Name
    2.31
    NAME
    2.06
     Names
    2.03
     naam
    1.98
     Namen
    1.97
    Activations Density 0.322%

    No Known Activations