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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 11056
    Prev
    Next
    INDEX
    Explanations

    terms related to temperature, heating, and heat-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.59
     يتيمه
    -0.58
    IsContent
    -0.56
     مرئيه
    -0.55
    }));
    
    -0.54
    cellaneous
    -0.53
     corren
    -0.53
    ()}}
    -0.52
     }));
    -0.51
     ngan
    -0.51
    POSITIVE LOGITS
     heat
    1.29
    Heat
    1.14
     hotter
    1.14
     warmth
    1.14
     temperature
    1.12
    heat
    1.11
     hot
    1.11
     Heat
    1.11
     temperatures
    1.07
     Temperatures
    1.06
    Activations Density 1.000%

    No Known Activations