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. 1084
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional struggle and the complexities of relationships

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

    Follows conversational pronouns

    np_acts-logits-general · gemini-2.0-flash

    my heart is like a river

    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
    :✨
    -0.71
     Juifs
    -0.62
     extrêmement
    -0.56
     relativamente
    -0.55
    setVerticalGroup
    -0.54
    ,“
    -0.54
     “¿
    -0.53
     extremadamente
    -0.53
     extremamente
    -0.53
     :).
    -0.51
    POSITIVE LOGITS
     GenerationType
    0.67
     gonna
    0.64
     you
    0.63
     tonight
    0.62
     
    0.62
     yeah
    0.61
     heut
    0.60
     oh
    0.59
     wanna
    0.59
    Chorus
    0.58
    Activations Density 0.165%

    No Known Activations