© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 12267
    Prev
    Next
    INDEX
    Explanations

    aspects of identity and representation in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.56
     Becoming
    -0.56
    étal
    -0.52
    Becoming
    -0.51
    fäl
    -0.50
    пли
    -0.49
     becoming
    -0.48
    netbeans
    -0.48
    Filt
    -0.47
     farsi
    -0.45
    POSITIVE LOGITS
     encourage
    0.74
    Encourage
    0.74
     Encourage
    0.74
     allow
    0.73
     saites
    0.72
     allowing
    0.70
     assign
    0.69
    Allow
    0.69
    让他们
    0.69
     letting
    0.69
    Activations Density 0.563%

    No Known Activations