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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6366
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationship building and fostering connections

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

    Texts about building relationships or infrastructure

    np_acts-logits-general · gemini-2.0-flash

    building relationships and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </>
    
    -0.39
    ||}
    -0.37
    >{@
    -0.36
    )*/
    -0.35
    CppMethod
    -0.35
    NamedQueries
    -0.34
    )=>{
    
    -0.34
    InitVars
    -0.34
    requireNonNull
    -0.34
    )";
    
    -0.33
    POSITIVE LOGITS
    Building
    0.97
     building
    0.95
    building
    0.90
     builder
    0.84
     membangun
    0.83
     Building
    0.82
     builders
    0.79
    builder
    0.79
     BUILDING
    0.79
    BUILDING
    0.76
    Activations Density 0.163%

    No Known Activations