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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14822
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss societal perceptions and cultural dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poveznice
    -0.45
     quieras
    -0.44
    GOTREF
    -0.40
     <<<<<<<<<<<<<<
    -0.38
     trouxe
    -0.38
    MemoryWarning
    -0.37
    Бахар
    -0.37
     defines
    -0.36
     Ober
    -0.36
     selve
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    0.60
    bootstrapcdn
    0.56
    KommentareTeilen
    0.51
     gynhyrchwyd
    0.46
     CreateTagHelper
    0.43
    ronpa
    0.41
     podob
    0.40
     join
    0.39
     ähnliche
    0.39
     like
    0.39
    Activations Density 0.480%

    No Known Activations