© 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. 14494
    Prev
    Next
    INDEX
    Explanations

    phrases related to persistence and resistance

    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
    1992
    +0.08
    0.2%
    581
    +0.08
    0.2%
    1218
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.08
    0.05
    1675
    +0.08
    0.05
    697
    +0.08
    0.05
    Negative Logits
     Intere
    -1.25
     affor
    -1.23
     increa
    -1.18
     desir
    -1.18
     effe
    -1.16
     chrysler
    -1.15
     dispen
    -1.13
     nece
    -1.11
     lamborghini
    -1.11
     fta
    -1.10
    POSITIVE LOGITS
    <bos>
    0.94
     nor
    0.92
     anymore
    0.71
    nor
    0.66
     anywhere
    0.64
     whatsoever
    0.60
     sondern
    0.59
    ]?.
    0.55
    Nor
    0.55
    droje
    0.51
    Activations Density 0.323%

    No Known Activations