© 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. 8414
    Prev
    Next
    INDEX
    Explanations

    phrases indicating social needs and connections

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

    "need" or a form of "need"

    np_acts-logits-general · gemini-2.0-flash

    expressing need

    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
     nahilalakip
    -0.51
    Ligações
    -0.49
    ssize
    -0.48
     estekak
    -0.47
     rospy
    -0.45
    itec
    -0.45
    DataField
    -0.45
    oboda
    -0.44
    Люби
    -0.44
    setPreferred
    -0.44
    POSITIVE LOGITS
     need
    2.06
     Need
    1.89
    need
    1.87
     needs
    1.82
     NEED
    1.81
    Need
    1.80
    NEED
    1.68
     Needs
    1.67
    needs
    1.64
    Needs
    1.62
    Activations Density 0.247%

    No Known Activations