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. 10841
    Prev
    Next
    INDEX
    Explanations

    terms related to relationships and connections among entities

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

    origin or separation

    np_acts-logits-general · gemini-2.0-flash

    extracting from source

    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
     resultCode
    -0.51
     ponta
    -0.51
     HasFactory
    -0.49
    IZONTAL
    -0.48
    WriteBarrier
    -0.44
    AddItem
    -0.42
     contamos
    -0.42
    løs
    -0.42
    ñora
    -0.42
     referrerpolicy
    -0.42
    POSITIVE LOGITS
     derive
    0.91
     deriving
    0.82
     derives
    0.81
     derived
    0.75
     Derived
    0.75
     eman
    0.70
     extracting
    0.69
     sprang
    0.69
    derived
    0.68
     extract
    0.68
    Activations Density 0.105%

    No Known Activations