© 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-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2335
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical relationships between entities, particularly focusing on parent and child relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }{$\
    -0.50
    bufio
    -0.46
    \#:
    -0.45
    }$\
    -0.45
    ')}}
    -0.44
    Jîn
    -0.44
    ++];
    -0.44
     chio
    -0.44
    #
    -0.43
    ToShow
    -0.43
    POSITIVE LOGITS
     Parent
    1.40
    Parent
    1.37
     parent
    1.29
    parent
    1.29
     PARENT
    1.16
     Parents
    1.16
    Parents
    1.11
     parents
    1.07
    setParent
    1.07
    PARENT
    1.06
    Activations Density 0.115%

    No Known Activations