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. 14-GEMMASCOPE-RES-16K
    6. 12869
    Prev
    Next
    INDEX
    Explanations

    expressions related to taking paths and journeys in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atividad
    -0.56
    pytest
    -0.51
    genstein
    -0.51
     ioutil
    -0.51
    persion
    -0.50
    ựu
    -0.49
     presence
    -0.47
    ModelSerializer
    -0.47
     Ehren
    -0.47
     présence
    -0.47
    POSITIVE LOGITS
     progress
    1.08
    StoryboardSegue
    1.06
     path
    1.03
     journey
    0.98
     toward
    0.97
     paths
    0.96
     towards
    0.96
    progress
    0.94
     Journey
    0.93
    towards
    0.91
    Activations Density 0.270%

    No Known Activations