© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10825
    Prev
    Next
    INDEX
    Explanations

    relationships between treatments and their efficacy on chronic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.47
    delwed
    -0.42
    Erreferentziak
    -0.42
    adpleegd
    -0.41
    OGND
    -0.36
    offsetof
    -0.36
     resourceCulture
    -0.36
     mapStateToProps
    -0.34
    OutputType
    -0.33
    WriteTagHelper
    -0.33
    POSITIVE LOGITS
     permanent
    2.53
    permanent
    2.23
     permanently
    2.06
     PERMAN
    2.05
    Permanent
    2.05
     Permanent
    2.02
     permanente
    1.94
    perman
    1.88
     permanence
    1.88
     Perman
    1.88
    Activations Density 1.039%

    No Known Activations