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. 22-GEMMASCOPE-RES-16K
    6. 16154
    Prev
    Next
    INDEX
    Explanations

    specific legal terminologies and references within text related to judicial processes

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

    Text preceding colons

    np_acts-logits-general · gemini-2.0-flash

    phrases followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -1.15
     فريبيس
    -1.11
    AddTagHelper
    -1.10
    ".
    
    -1.00
    ).</
    -0.96
    StoryboardSegue
    -0.95
    $.
    
    -0.94
     />';
    -0.94
    NUMX
    -0.94
    .")]
    -0.93
    POSITIVE LOGITS
    :
    3.35
    :
    
    2.22
    :
    2.20
     :
    2.17
    ():
    2.06
    ):
    2.02
    :}
    2.01
    :</
    1.90
    ':
    1.87
    ":
    1.87
    Activations Density 5.138%

    No Known Activations