Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3839
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a necessity or demand for improvements or solutions in various contexts

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

    "need" or its synonyms

    np_acts-logits-general · gemini-2.0-flash

    there is a need for

    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
     JpaRepository
    -0.51
     estekak
    -0.48
     Exactos
    -0.47
     kaarangay
    -0.47
     Autorizaciones
    -0.47
    intios
    -0.46
     CreateTagHelper
    -0.43
    issory
    -0.42
    RotationOrder
    -0.42
    Спасылкі
    -0.42
    POSITIVE LOGITS
     need
    0.84
    need
    0.80
     Need
    0.76
    Need
    0.75
     NEED
    0.73
     варто
    0.67
     Perlu
    0.64
     bisogno
    0.63
    NEED
    0.62
     слід
    0.59
    Activations Density 0.377%

    No Known Activations