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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 998
    Prev
    Next
    INDEX
    Explanations

    the verb "know" and related terms such as "knowingly" or "where"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1376
    +0.15
    0.5%
    1757
    +0.14
    0.5%
    201
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.15
    0.05
    1376
    +0.14
    0.06
    1068
    +0.13
    0.06
    Negative Logits
     optik
    -0.75
     Strukt
    -0.60
     ekos
    -0.56
     antik
    -0.56
     silikon
    -0.53
     organik
    -0.53
     seksi
    -0.53
     minimalis
    -0.52
     kristal
    -0.51
     Demokrat
    -0.51
    POSITIVE LOGITS
    know
    1.15
    Know
    1.09
     know
    1.07
     Know
    1.05
     KNOW
    1.00
     knows
    0.97
    knows
    0.93
    knew
    0.89
    KNOW
    0.87
     knew
    0.85
    Activations Density 0.145%

    No Known Activations