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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 5495
    Prev
    Next
    INDEX
    Explanations

    pronouns and the presence of stock or option references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inette
    -0.44
     bu
    -0.42
     heller
    -0.41
    eve
    -0.41
     most
    -0.40
     it
    -0.40
     Is
    -0.40
    JNIEnv
    -0.39
     not
    -0.38
     wann
    -0.38
    POSITIVE LOGITS
    mereka
    1.14
    Their
    1.14
    Mereka
    1.13
    They
    1.12
    彼らの
    1.05
     They
    1.05
     they
    1.03
    they
    1.01
     THEY
    0.99
    彼らは
    0.99
    Activations Density 0.394%

    No Known Activations